© 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. 61928
    Prev
    Next
    INDEX
    Explanations

    courses and training

    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
    绳
    -0.09
    åĿļå®Ī
    -0.09
    åĩºåĬ¨
    -0.09
    SCRI
    -0.09
    _ACL
    -0.08
    isempty
    -0.08
    åĪĿæŃ¥
    -0.08
     задаÑĩ
    -0.08
    AttributeValue
    -0.08
    quete
    -0.08
    POSITIVE LOGITS
    æİĪ课
    0.17
    åŁ¹è®Ń
    0.16
    åѦåijĺ
    0.14
    åIJ¬è¯¾
    0.14
    课ç¨ĭ
    0.14
    ä¼łæİĪ
    0.13
    åŁ¹è®ŃæľºæŀĦ
    0.13
    åŃ¦ä¹ł
    0.13
    æĬ¥åIJį
    0.12
    åŁ¹è®ŃçıŃ
    0.12
    Activations Density 0.270%

    No Known Activations