© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4093
    Prev
    Next
    INDEX
    Explanations

    building on the rich heritage...""...upon the pioneering work...""...built upon the foundation...""...building upon an effective piano groove...""...expand on the traditional cell phone functionality...""...present invention relates to...""...ological University, Pathein..."building on or upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    linger
    -0.11
    对æłĩ
    -0.10
    ç»Łè®¡å±Ģ
    -0.09
    绡
    -0.09
    Exclusive
    -0.09
    dsl
    -0.09
    exclusive
    -0.09
    anged
    -0.09
    åħ¬æĬ¥
    -0.09
    lung
    -0.09
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.12
     previously
    0.10
     existing
    0.10
     previous
    0.10
    å·²æľī
    0.09
    åİŁæľī
    0.09
     Existing
    0.09
    ä¸Ģå±Ĥ
    0.09
    ADE
    0.09
    å·²
    0.09
    Activations Density 0.028%

    No Known Activations