© 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. 63598
    Prev
    Next
    INDEX
    Explanations

    /wiki links

    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
    ForKey
    -0.11
    æķķ
    -0.09
    é£İæĻ¯
    -0.09
    寡
    -0.09
    åħĴ
    -0.09
    åĵºä¹³
    -0.09
    ree
    -0.09
    zee
    -0.09
    (dec
    -0.09
    æĽĻ
    -0.08
    POSITIVE LOGITS
    ìĹŃ
    0.09
    èĢ½è¯¯
    0.08
    atu
    0.08
    ETS
    0.08
    èIJ½å®ŀ
    0.08
    ائب
    0.08
    hatt
    0.08
    ç¥ŀç»ıç³»ç»Ł
    0.08
    ä¹ł
    0.08
    æ±ĩæĬ¥
    0.07
    Activations Density 0.096%

    No Known Activations