© 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. 50130
    Prev
    Next
    INDEX
    Explanations

    judge and judgment

    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
    icker
    -0.11
    ests
    -0.09
    esty
    -0.09
    enders
    -0.09
    é¼IJ
    -0.08
    оÑĦ
    -0.08
    atego
    -0.08
    è¿ĽäºĨ
    -0.08
    .decorate
    -0.08
     Newsp
    -0.08
    POSITIVE LOGITS
    èĥľè´Ł
    0.11
    åĪ¤å®ļ
    0.10
    失误
    0.09
     judge
    0.09
    éľľ
    0.09
    ä¸ĩåħĥ以ä¸Ĭ
    0.08
    ä¸įåĩºæĿ¥
    0.08
    gement
    0.08
    èĩªåľ¨
    0.08
    å·¦åı³
    0.08
    Activations Density 0.035%

    No Known Activations