© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6263
    Prev
    Next
    INDEX
    Explanations

    software, license, relation

    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
    Negative Logits
    ç¾İæľ¯é¦Ĩ
    -0.10
    ÑģлÑĥÑĪ
    -0.10
    Hosting
    -0.09
    ä¸Ģ家人
    -0.09
    âĵĴ
    -0.08
    _Public
    -0.08
    dsa
    -0.08
    æ®ĸ
    -0.08
    åķľ
    -0.08
    大å¤ļæķ°äºº
    -0.08
    POSITIVE LOGITS
    æĿĵ
    0.11
    akan
    0.10
    allet
    0.09
    ocracy
    0.08
    éĻįèĩ³
    0.08
    .argument
    0.08
    äºī缸
    0.08
    çŧ
    0.08
    æ²»
    0.08
    ä»İæľª
    0.08
    Activations Density 0.007%

    No Known Activations