© 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. 34275
    Prev
    Next
    INDEX
    Explanations

    derivative 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
    QUI
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    主è§Ĥ
    -0.09
    èĩªæѤ
    -0.09
    èĤ©
    -0.08
    çĽ¸äº²
    -0.08
    xec
    -0.08
     dec
    -0.08
    ioned
    -0.08
     Pact
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥æ´»åĬ¨
    0.09
    ä¸įéĢļ
    0.09
    æĹłæīĢ
    0.09
    ÑĹ
    0.09
    è¸Į
    0.09
    åıįæŃ£
    0.09
    èĢ·
    0.09
    å±ij
    0.08
     PV
    0.08
     Christoph
    0.08
    Activations Density 0.005%

    No Known Activations