© 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. 2316
    Prev
    Next
    INDEX
    Explanations

    http links and comments

    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
    åİĨå¹´
    -0.08
    çĽ¼
    -0.08
    åıįæŃ£
    -0.08
    åĮºåŁŁæĢ§
    -0.08
    褪
    -0.07
    ãģĵãģĨ
    -0.07
    http
    -0.07
    -0.07
     бÑĥд
    -0.07
    FER
    -0.07
    POSITIVE LOGITS
    _goto
    0.11
    byn
    0.10
    æĿ³
    0.10
    ä¹İ
    0.09
    ÑĢед
    0.09
    ç»ĨåĪĻ
    0.09
    bild
    0.09
    ÑĨиÑı
    0.09
     urz
    0.09
     ÙĪØ¥ÙĨ
    0.08
    Activations Density 0.164%

    No Known Activations