© 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. 34603
    Prev
    Next
    INDEX
    Explanations

    McCormack / lex

    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
    å·¥ä½ľå®¤
    -0.09
     huyết
    -0.08
    _tickets
    -0.08
    oux
    -0.08
    ä½ķåĨµ
    -0.08
    è¡ĮæĶ¿éĥ¨éŨ
    -0.08
    aced
    -0.08
    ãģ»ãģĨ
    -0.08
    çľĩ
    -0.08
    Hidden
    -0.08
    POSITIVE LOGITS
    çIJĨä¼ļ
    0.10
    INAL
    0.09
    mercial
    0.09
    opy
    0.09
    shield
    0.09
    OPY
    0.09
    ments
    0.09
    ä»»æĢ§
    0.09
    ÙĩاÙħ
    0.08
    ismo
    0.08
    Activations Density 0.004%

    No Known Activations