© 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. 55614
    Prev
    Next
    INDEX
    Explanations

    near locations

    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
    /ph
    -0.09
    ä¸ĭéĿ¢æĺ¯
    -0.09
    INGER
    -0.08
     spec
    -0.08
    isko
    -0.08
    大æ°Ķ
    -0.08
    ÑĪка
    -0.08
    çĪ±åĽ½
    -0.08
    éī´äºİ
    -0.08
     outr
    -0.07
    POSITIVE LOGITS
    åĵŃ
    0.09
    çĻ½é©¬
    0.09
     Cran
    0.09
    设ç«ĭäºĨ
    0.09
    äºijéĽĨ
    0.08
     cul
    0.08
    uments
    0.08
    伤çĹħ
    0.08
    _placeholder
    0.08
    _inst
    0.08
    Activations Density 0.037%

    No Known Activations