© 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. 31256
    Prev
    Next
    INDEX
    Explanations

    sentenced to years or probation

    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
    被çĽĹ
    -0.10
    виÑģ
    -0.10
     Toll
    -0.09
    æīĢåľ¨
    -0.09
    èĻIJ
    -0.09
    .opensource
    -0.09
    _RM
    -0.09
    è°
    -0.09
    yth
    -0.08
    hem
    -0.08
    POSITIVE LOGITS
    ä¸İä¼Ĺ
    0.09
    èĵĸ
    0.09
    æŃ»åIJİ
    0.08
    ãģĤãĤĬãģ¾ãģĽãĤĵ
    0.08
    å°ij许
    0.08
    ç¿İ
    0.08
    ãģªãĤīãģªãģĦ
    0.08
    ä¸Ģåľº
    0.08
     Civ
    0.07
    å¾®ç¬ij
    0.07
    Activations Density 0.019%

    No Known Activations