© 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. 23239
    Prev
    Next
    INDEX
    Explanations

    help prevent or reduce negative outcomes

    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
    è°Ĭ
    -0.09
    hec
    -0.09
    å®ĥ
    -0.09
    oun
    -0.09
    ä¸Ģæī¹
    -0.08
    åĬ©åĬĽ
    -0.08
    ograd
    -0.08
     Äijiá»ĥn
    -0.08
    ten
    -0.08
    åı£å¤´
    -0.08
    POSITIVE LOGITS
    åĥŃ
    0.09
     cân
    0.09
    ç±į
    0.08
    妪
    0.08
    辫
    0.08
    ãģĵãģ¨ãģ¯
    0.08
    isons
    0.08
    ForResource
    0.08
    uby
    0.08
    åĵ
    0.08
    Activations Density 0.025%

    No Known Activations