© 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. 18808
    Prev
    Next
    INDEX
    Explanations

    logistic regression

    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
    andest
    -0.09
    _stylesheet
    -0.09
     gener
    -0.09
    nak
    -0.09
    _LR
    -0.09
    rets
    -0.09
    ÑģÑĤа
    -0.08
    ä½ľ
    -0.08
    yah
    -0.08
    yard
    -0.08
    POSITIVE LOGITS
    imal
    0.10
     kali
    0.09
    身å¤Ħ
    0.09
     ÐĴлад
    0.09
    ä¸įä¸ĭ
    0.09
    åĽ½æĥħ
    0.08
    wards
    0.08
    èĩ¨
    0.08
    oid
    0.08
    clipse
    0.08
    Activations Density 0.002%

    No Known Activations