© 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. 2093
    Prev
    Next
    INDEX
    Explanations

    beginning of

    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
    ify
    -0.10
    sdale
    -0.09
    alysis
    -0.09
    anh
    -0.09
    lock
    -0.09
    acters
    -0.09
    ification
    -0.08
    صÙĦ
    -0.08
    ocracy
    -0.08
    ï¸ı
    -0.08
    POSITIVE LOGITS
    OfDay
    0.11
    /end
    0.10
    éĴ¤
    0.10
    orse
    0.09
    /native
    0.09
    OfString
    0.09
    OfMonth
    0.09
     eget
    0.09
    gs
    0.08
    endor
    0.08
    Activations Density 0.021%

    No Known Activations