© 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. 63333
    Prev
    Next
    INDEX
    Explanations

    proportional to or order of

    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
     overcrow
    -0.08
    缸ç»ĵåIJĪ
    -0.07
    LLU
    -0.07
    Execution
    -0.07
    eder
    -0.07
    磨
    -0.07
     Libert
    -0.07
    åİŁæľī
    -0.07
    ç¥ŀç»ıç³»ç»Ł
    -0.07
    åīįä¸Ģ天
    -0.07
    POSITIVE LOGITS
     оÑĤноÑĪ
    0.10
    éĴľ
    0.09
    ê°Ĵ
    0.09
    åĩłåĪĨ
    0.09
    åĢ¼
    0.08
     relations
    0.08
     deÄŁ
    0.08
    åħ³ç³»
    0.08
    秸
    0.08
    ä»ĸèĩªå·±
    0.08
    Activations Density 0.743%

    No Known Activations