© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36771
    Prev
    Next
    INDEX
    Explanations

    eligible for

    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
    isper
    -0.09
    _PB
    -0.08
    HEN
    -0.08
    é¢Ĥ
    -0.08
    илÑĮно
    -0.08
     Sands
    -0.08
    BAT
    -0.08
    积
    -0.08
    acity
    -0.08
    _GENERAL
    -0.08
    POSITIVE LOGITS
    èĻļæŀĦ
    0.09
    æ°ijå¿ĥ
    0.09
    åĸĩåıŃ
    0.08
    éĢıè¿ĩ
    0.08
    ä¸ºæľŁ
    0.08
    reds
    0.08
    /use
    0.08
    æĥħåĨµè¿Ľè¡Į
    0.08
    amp
    0.08
    为ä¹ĭ
    0.08
    Activations Density 0.023%

    No Known Activations