© 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. 2282
    Prev
    Next
    INDEX
    Explanations

    numbers in ranges like tens, hundreds, thousands

    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·Ŀ离
    -0.11
    è·ĿéĽ¢
    -0.10
     Distance
    -0.10
    _DISTANCE
    -0.10
    distance
    -0.09
    Distance
    -0.09
    人人éĥ½
    -0.09
    wayne
    -0.09
    ä¸Ģ段
    -0.09
    éĹ´éļĶ
    -0.09
    POSITIVE LOGITS
    stre
    0.09
    é¢ľ
    0.09
    èµŀç¾İ
    0.09
     Cla
    0.08
    rais
    0.08
    纯åĩĢ
    0.08
    éĿ¢éĥ¨
    0.08
    lands
    0.08
     numbered
    0.08
    ики
    0.08
    Activations Density 0.053%

    No Known Activations