© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38140
    Prev
    Next
    INDEX
    Explanations

    media or publication sources

    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
    æ°¸
    -0.09
    åįģ足
    -0.07
    äºĺ
    -0.07
    reed
    -0.07
     o
    -0.07
     lou
    -0.07
     Ấ
    -0.07
     Wh
    -0.07
    åĽĽåŃ£
    -0.07
    æŃĮ
    -0.07
    POSITIVE LOGITS
    atars
    0.11
    _VO
    0.11
    LEGAL
    0.10
    ensch
    0.10
    ['__
    0.10
    å¦Ĥæŀľä¸įæĺ¯
    0.10
    è¾Ł
    0.10
    synthesize
    0.10
    责任ç¼ĸè¾ij
    0.10
    æķ´çIJĨ
    0.10
    Activations Density 0.075%

    No Known Activations