© 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. 34160
    Prev
    Next
    INDEX
    Explanations

    new delhi

    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
    hips
    -0.10
    åħ¨æĸĩ
    -0.09
    åħĪè¿ĽæĬĢæľ¯
    -0.09
    ëŀĢ
    -0.08
    ked
    -0.08
    æľ¬ç½ij
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    arry
    -0.08
    hip
    -0.08
    ilet
    -0.08
    POSITIVE LOGITS
    é£İæļ´
    0.11
    æµ·æ·ĢåĮº
    0.10
    è¿Ļ件
    0.09
    æµ·æ·Ģ
    0.09
    ANCE
    0.09
    å¸ĪèĮĥ大åѦ
    0.09
     IGNORE
    0.09
    ä¸įæ¸ħ
    0.09
    à¹Ħ
    0.09
    Ñģко
    0.09
    Activations Density 0.016%

    No Known Activations