© 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. 11798
    Prev
    Next
    INDEX
    Explanations

    Lee followed by a name

    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
    sWith
    -0.13
    eur
    -0.10
    ย
    -0.10
    ially
    -0.10
    nya
    -0.10
    arily
    -0.10
    ErrorException
    -0.09
    mente
    -0.09
    ally
    -0.09
    ials
    -0.09
    POSITIVE LOGITS
    á»ĩt
    0.10
    æī«ä¸Ģæī«
    0.10
    REN
    0.09
    ision
    0.09
    æ·Ģ
    0.09
    -même
    0.09
    uten
    0.09
     breeze
    0.08
    ropping
    0.08
    bove
    0.08
    Activations Density 0.020%

    No Known Activations