© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19985
    Prev
    Next
    INDEX
    Explanations

    can be, could be

    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
    phan
    -0.09
    åŁ
    -0.09
    åĴĮæĶ¯æĮģ
    -0.08
    çĸı
    -0.08
    åĨĴ
    -0.08
    é¹ħ
    -0.08
    ADOS
    -0.08
    _MSB
    -0.08
    åĪĨæīĭ
    -0.08
    anca
    -0.08
    POSITIVE LOGITS
    è¿Ļ对äºİ
    0.09
    è¿Ļ对
    0.09
    好å¤ļ
    0.09
    åĽ½éĻħåľ¨çº¿
    0.09
    建çŃijå¸Ī
    0.09
    åķĸ
    0.08
    èĥ½åģļåĪ°
    0.08
     consul
    0.08
    .proc
    0.08
    æ±Ń
    0.08
    Activations Density 0.004%

    No Known Activations