© 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. 36568
    Prev
    Next
    INDEX
    Explanations

    despite

    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
    _unsigned
    -0.11
    roma
    -0.10
    äº²çľ¼
    -0.09
    xAF
    -0.09
    alus
    -0.09
    Ñĥз
    -0.09
    çĽĹ
    -0.09
    æĦıæĢĿæĺ¯
    -0.09
    еннÑĭе
    -0.09
    éĩįå¿ĥ
    -0.09
    POSITIVE LOGITS
    ively
    0.11
    ably
    0.10
    æľī个
    0.09
    forth
    0.09
     being
    0.09
    ãģĤãĤĭç¨ĭ度
    0.08
    fy
    0.08
    bei
    0.08
    emente
    0.08
    zes
    0.08
    Activations Density 0.023%

    No Known Activations