© 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. 54270
    Prev
    Next
    INDEX
    Explanations

    good reputation or fame

    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
     Pron
    -0.08
    åı¸é©¬
    -0.08
    ç½Ĺ
    -0.08
    æ¸ł
    -0.08
    èĽĽ
    -0.08
    ár
    -0.07
    ote
    -0.07
    inel
    -0.07
    éļIJèĶ½
    -0.07
    离
    -0.07
    POSITIVE LOGITS
     reputation
    0.25
    声èªī
    0.23
    åIJį声
    0.23
     Reputation
    0.22
     reput
    0.20
    ä¿¡èªī
    0.18
    åı£ç¢ij
    0.17
    ç¾İèªī
    0.17
    åIJįèªī
    0.16
     fame
    0.15
    Activations Density 0.050%

    No Known Activations