© 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. 11290
    Prev
    Next
    INDEX
    Explanations

    cosmetics, cosmid, cosplayers, cosmo

    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
    ness
    -0.11
    icker
    -0.09
    罪
    -0.09
    ivers
    -0.09
    alam
    -0.09
    esse
    -0.09
    воÑĢ
    -0.09
    åĬ²
    -0.08
    reur
    -0.08
    \views
    -0.08
    POSITIVE LOGITS
    metics
    0.10
    é¢ľ
    0.09
    unter
    0.09
    ftware
    0.09
    wik
    0.09
    MLS
    0.09
    人æµģ
    0.09
    pill
    0.09
    folk
    0.09
    metic
    0.08
    Activations Density 0.016%

    No Known Activations