© 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. 53881
    Prev
    Next
    INDEX
    Explanations

    url, code, or special characters

    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
    ensive
    -0.09
    omer
    -0.09
    纶
    -0.09
    è´¡çĮ®åĬĽéĩı
    -0.09
    oller
    -0.09
    olt
    -0.09
    å¥Ħ
    -0.09
    aus
    -0.09
    æįº
    -0.09
    ÑĢÑĥж
    -0.09
    POSITIVE LOGITS
    ä¸Ģæĺ¯
    0.09
    çļĦå°±æĺ¯
    0.09
    ainless
    0.08
    ä¸Ģæĸ¹éĿ¢
    0.08
    Cong
    0.08
    åħ´å¥ĭ
    0.08
    ä¸ĢæŃ¥æŃ¥
    0.08
    MBED
    0.08
    bins
    0.08
    èħ¹
    0.07
    Activations Density 0.735%

    No Known Activations