© 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. 62543
    Prev
    Next
    INDEX
    Explanations

    user related actions

    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
    躬
    -0.11
    uddle
    -0.10
    ç¾½
    -0.10
    让人们
    -0.09
    åıĹ访
    -0.09
    æĨ¾
    -0.09
    _iso
    -0.09
    åŀł
    -0.09
    ä¸ĸ人
    -0.09
    ç»Ĩå¾®
    -0.09
    POSITIVE LOGITS
    =User
    0.11
    (User
    0.10
    çķĮéĿ¢
    0.10
    itarian
    0.10
    innen
    0.09
    elin
    0.09
     frank
    0.09
    大ä¼ļ
    0.08
    hip
    0.08
    uide
    0.08
    Activations Density 0.155%

    No Known Activations