© 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. 5529
    Prev
    Next
    INDEX
    Explanations

    new partner or replacement

    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
    åIJĮä»ģ
    -0.10
    igator
    -0.09
    ç¼
    -0.09
    éģĴ
    -0.09
    brit
    -0.09
    Ấ
    -0.09
    è°¬
    -0.08
    _ask
    -0.08
    è²ī
    -0.08
    _Parameter
    -0.08
    POSITIVE LOGITS
    æĺ¯è°ģ
    0.11
    ãģĦãģªãģĦ
    0.09
    纳
    0.09
    å§ĵ
    0.09
    èĽĭ
    0.09
    åĨ²åĪº
    0.09
    仪表
    0.09
    åIJĪéĢĤ
    0.09
    è§ĤæľĽ
    0.09
    anus
    0.08
    Activations Density 0.084%

    No Known Activations