© 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. 5463
    Prev
    Next
    INDEX
    Explanations

    school districts

    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
    reff
    -0.09
    æīĵå¾Ĺ
    -0.08
    å¨ģåĬĽ
    -0.08
    datap
    -0.08
    ubar
    -0.08
    perience
    -0.08
    avs
    -0.07
    èĵij
    -0.07
    éĥľ
    -0.07
     flu
    -0.07
    POSITIVE LOGITS
    å®ĺåijĺ
    0.11
    éŨåı£
    0.10
    RELEASE
    0.10
     Sparks
    0.10
    ä¿Ń
    0.10
     officials
    0.09
    ignon
    0.09
    红线
    0.09
    urre
    0.09
    ä¸ĩåIJį
    0.09
    Activations Density 0.018%

    No Known Activations