© 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. 58975
    Prev
    Next
    INDEX
    Explanations

    ZTE, Perry, Street, Wooden, Lo

    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
    plates
    -0.09
    .tk
    -0.09
    shi
    -0.08
    actic
    -0.08
    ãģ¤ãģı
    -0.08
    害
    -0.08
    ä¸įå¿į
    -0.08
    аÑĪ
    -0.08
     plates
    -0.08
    æ²ĥ
    -0.08
    POSITIVE LOGITS
    ä»ĭ
    0.10
    olib
    0.10
    THON
    0.10
    åħ¸ç¤¼
    0.09
    ebra
    0.09
     DeV
    0.09
    棵
    0.08
    ilate
    0.08
    Joe
    0.08
    éļıæīĭ
    0.08
    Activations Density 0.146%

    No Known Activations