© 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. 33723
    Prev
    Next
    INDEX
    Explanations

    shadow

    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
    uset
    -0.10
    ucc
    -0.09
     latter
    -0.09
    æ²½
    -0.09
    usk
    -0.09
    Ñģо
    -0.08
    丰ç¡ķ
    -0.08
    sel
    -0.08
    asion
    -0.08
    ivity
    -0.08
    POSITIVE LOGITS
    mour
    0.11
    edBy
    0.10
    å¯IJ
    0.10
    ed
    0.10
    ering
    0.10
    ry
    0.10
    ood
    0.10
    edList
    0.10
    lines
    0.09
    cuts
    0.09
    Activations Density 0.021%

    No Known Activations