© 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. 31419
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    empo
    -0.09
    çĦĺ
    -0.09
    æĢĿç´¢
    -0.09
     Dexter
    -0.08
     Wick
    -0.08
    澡
    -0.08
    _tp
    -0.08
     thá»ķ
    -0.08
    好åIJĹ
    -0.08
    aines
    -0.08
    POSITIVE LOGITS
    åİĨå¹´
    0.09
    ç¾İ丽çļĦ
    0.09
    éĿłè°±
    0.09
    ä»İæĿ¥ä¸į
    0.08
    没åħ³ç³»
    0.08
    è°
    0.08
    ãģĤãĤĭ
    0.08
    slashes
    0.08
    尽管
    0.08
    åģļä¸Ģ个
    0.08
    Activations Density 0.159%

    No Known Activations