© 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. 57355
    Prev
    Next
    INDEX
    Explanations

    disconnect or disjunction

    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
    ä¸įçĶ±
    -0.10
    ä¸įåĨįæĺ¯
    -0.09
    ä¸įä¸Ĭ
    -0.09
     sơ
    -0.09
    å½ĵä¹ĭ
    -0.08
    Agency
    -0.08
    诱æĥij
    -0.08
    ikon
    -0.08
    çŃ¹å»º
    -0.08
    skins
    -0.08
    POSITIVE LOGITS
    æĥ³äºĨ
    0.10
    é«ĺæ°´å¹³
    0.09
    FromClass
    0.09
    æ¿ĢçĥĪçļĦ
    0.09
    íķĺëĭ¤
    0.09
    lle
    0.09
    .Dis
    0.09
    ä½Ĩä»İ
    0.09
    adic
    0.08
    ValueType
    0.08
    Activations Density 0.031%

    No Known Activations