© 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. 30025
    Prev
    Next
    INDEX
    Explanations

    pop culture figures, names, and associated actions

    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
    è§
    -0.11
    满足
    -0.10
    è¥Ħ
    -0.10
    /XMLSchema
    -0.10
    éĩijåŃĹ
    -0.10
    .MEDIA
    -0.10
    /xhtml
    -0.10
    æ¶İ
    -0.09
    åĢļ
    -0.09
    çĨı
    -0.09
    POSITIVE LOGITS
    æĹ¥å¤ľ
    0.09
    æĺ¼å¤ľ
    0.08
    _gap
    0.08
    us
    0.08
    TTY
    0.08
    0
    0.08
    é¢
    0.08
    5
    0.07
    enger
    0.07
    3
    0.07
    Activations Density 0.620%

    No Known Activations