© 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. 31406
    Prev
    Next
    INDEX
    Explanations

    film context

    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
    ãģªãĤĤãģ®
    -0.09
    大å¦Ī
    -0.09
    di
    -0.09
    psc
    -0.09
    漫
    -0.08
    rum
    -0.08
    dy
    -0.08
    æ®·
    -0.08
    erb
    -0.08
    _fm
    -0.08
    POSITIVE LOGITS
    oteca
    0.11
    lets
    0.10
    strip
    0.10
    plementation
    0.10
    ographer
    0.10
     Starr
    0.09
    zik
    0.09
    à¸ķร
    0.09
    vana
    0.09
    licity
    0.09
    Activations Density 0.063%

    No Known Activations