© 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. 62206
    Prev
    Next
    INDEX
    Explanations

    serious, seriously

    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
    RAR
    -0.09
    egg
    -0.09
    èĬ±
    -0.08
    ç¹ģ
    -0.08
     ÑĥÑģл
    -0.08
    å°ı康
    -0.08
    ulen
    -0.08
    ogh
    -0.08
    สะà¸Ķ
    -0.08
    èѬ
    -0.08
    POSITIVE LOGITS
    严èĤĥ
    0.17
     Serious
    0.14
     ÑģеÑĢÑĮ
    0.12
     serious
    0.12
    è®¤çľŁ
    0.11
    åī
    0.11
    泪水
    0.11
    serious
    0.10
    åĪĽæĸ°é©±åĬ¨
    0.10
    å¿ĥæĥ³
    0.10
    Activations Density 0.026%

    No Known Activations