© 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. 47788
    Prev
    Next
    INDEX
    Explanations

    statewide, nationwide, countrywide, citywide

    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
    наÑĤ
    -0.09
    åŃĽ
    -0.09
    ÑĤеÑĢ
    -0.09
    /slider
    -0.08
    qua
    -0.08
     вÑĢемени
    -0.08
    rey
    -0.08
    TING
    -0.08
    inas
    -0.08
    wiÄĻ
    -0.08
    POSITIVE LOGITS
    est
    0.11
    onne
    0.11
    erton
    0.10
    ä»Ģ
    0.10
    leep
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    emen
    0.09
    icz
    0.09
    pread
    0.09
    ep
    0.09
    Activations Density 0.006%

    No Known Activations