© 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. 53440
    Prev
    Next
    INDEX
    Explanations

    can/pop/put/turn/receive/firms/smart

    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
     dec
    -0.08
    GRE
    -0.08
    è¾ĸåĮºåĨħ
    -0.08
    æī£
    -0.08
    Ùģار
    -0.08
    æĺ¨
    -0.08
    åĨ¯
    -0.08
    ä¸»åľº
    -0.07
    缤
    -0.07
     pip
    -0.07
    POSITIVE LOGITS
    磫
    0.10
    çij°
    0.10
     ningu
    0.09
    è¿Ļæł·åģļ
    0.09
    èĪįå¾Ĺ
    0.09
    Formatting
    0.09
     Enumerator
    0.09
    à¸Ŀาà¸ģ
    0.09
    rijk
    0.09
    THR
    0.08
    Activations Density 0.067%

    No Known Activations