© 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. 6737
    Prev
    Next
    INDEX
    Explanations

    Inc or Jr

    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¸įäºĨ
    -0.11
    峪
    -0.10
    าย
    -0.09
    æµ´
    -0.09
    ArrayOf
    -0.09
    гÑĥ
    -0.09
    .gms
    -0.09
    ÑĤÑĢ
    -0.08
    /logging
    -0.08
    yers
    -0.08
    POSITIVE LOGITS
    0.15
    ï¸ı
    0.14
    Ùĭ
    0.14
    Ùı
    0.10
    ÙIJ
    0.10
    å¹´å¤ľ
    0.09
    Ùij
    0.09
    Âł
    0.09
    StatusCode
    0.09
    à¹Į
    0.09
    Activations Density 0.294%

    No Known Activations