© 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. 61402
    Prev
    Next
    INDEX
    Explanations

    -based or driven

    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
    mention
    -0.09
     Loves
    -0.09
    /vendor
    -0.08
    åĮĸè¿Ľç¨ĭ
    -0.08
    èį§
    -0.08
    standing
    -0.08
    ubo
    -0.08
    Persist
    -0.08
    èĢ¸
    -0.08
    颧
    -0.07
    POSITIVE LOGITS
     approach
    0.11
    èĢĮä¸įæĺ¯
    0.11
    èĢĮéĿŀ
    0.11
     APPRO
    0.10
     Approach
    0.10
    ç©°
    0.09
    åŀĭä¼ģä¸ļ
    0.09
    æīĵæ³ķ
    0.09
     ìĦ¸ìĥģ
    0.09
    appro
    0.09
    Activations Density 0.139%

    No Known Activations