© 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. 27183
    Prev
    Next
    INDEX
    Explanations

    free software license

    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
    iveness
    -0.09
    istics
    -0.09
    rest
    -0.08
     salmon
    -0.08
    çļĦå¿ĥæĥħ
    -0.08
    éĻĮ
    -0.08
    å§ij
    -0.08
    ingly
    -0.08
     Viv
    -0.08
    isos
    -0.08
    POSITIVE LOGITS
    æ¼Ĥæµģ
    0.09
    ç¬ij声
    0.09
    LERÄ°
    0.08
     Sty
    0.08
    éĢł
    0.08
    å¾Ģè¿Ķ
    0.08
    çѱ
    0.08
    åīįåIJİ
    0.08
    verted
    0.08
    éģģ
    0.08
    Activations Density 0.031%

    No Known Activations