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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8864
    Prev
    Next
    INDEX
    Explanations

    Seniors

    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
    agn
    -0.10
    sWith
    -0.10
    ãģĤãģ£ãģŁ
    -0.10
     eens
    -0.09
    ment
    -0.09
    te
    -0.09
    ï¸ı
    -0.09
    sp
    -0.09
    æł·çļĦ
    -0.09
    spm
    -0.09
    POSITIVE LOGITS
    heimer
    0.11
    quential
    0.11
    itized
    0.10
    iors
    0.10
    urope
    0.10
    itize
    0.10
    èĩ¾
    0.10
    quence
    0.10
    elize
    0.10
    flower
    0.09
    Activations Density 0.020%

    No Known Activations