© 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. 37825
    Prev
    Next
    INDEX
    Explanations

    given names

    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
    damn
    -0.09
    emo
    -0.09
    dam
    -0.09
     Ñĥзн
    -0.08
    å¦Ĥä»Ĭ
    -0.08
    ymbols
    -0.08
    ноп
    -0.08
    olib
    -0.08
    楣
    -0.08
     damit
    -0.08
    POSITIVE LOGITS
    ä¹ĭ乡
    0.09
    ä¿®åħ»
    0.09
    ï¸ı
    0.09
    è®°èĢħéĩĩ访
    0.09
    äºĭ迹
    0.08
    Ñĥ
    0.08
    绳
    0.08
    å´Ĩ
    0.08
    ç«Ļèµ·æĿ¥
    0.08
    éĽĨèģļ
    0.08
    Activations Density 0.108%

    No Known Activations