© 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. 9914
    Prev
    Next
    INDEX
    Explanations

    colombian

    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
    ugen
    -0.10
    çĥŁåĽ±
    -0.09
    产æĿĥ
    -0.09
    otta
    -0.09
     Lion
    -0.08
     пÑĢава
    -0.08
    oyal
    -0.08
     deduction
    -0.08
    zik
    -0.08
     keen
    -0.08
    POSITIVE LOGITS
    迤
    0.10
    ç¿İ
    0.10
    æĽ²
    0.09
    _PIX
    0.09
    BOOT
    0.09
    illos
    0.08
    é»ĺå¥ij
    0.08
    å¯Ĥå¯ŀ
    0.08
    åĵ¥ä¼¦æ¯Ķäºļ
    0.08
    spr
    0.08
    Activations Density 0.071%

    No Known Activations