© 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. 53690
    Prev
    Next
    INDEX
    Explanations

    free downloads

    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
    acic
    -0.10
    ÑįÑĢ
    -0.10
    avel
    -0.10
    ittest
    -0.09
    .getvalue
    -0.09
    reachable
    -0.09
    gart
    -0.09
     ÑģовеÑĢÑĪен
    -0.09
    ÐIJÐĿ
    -0.08
    Æ°u
    -0.08
    POSITIVE LOGITS
    åľ¨æ¸¸æĪıä¸Ń
    0.09
     reasons
    0.09
     Wolff
    0.08
     Reasons
    0.08
    å°±è¿Ļæł·
    0.08
    éĢģåĩº
    0.08
    upos
    0.08
    åİŁåĽłä¹ĭä¸Ģ
    0.08
    alse
    0.08
    å°ıä¼Ļ伴们
    0.08
    Activations Density 0.006%

    No Known Activations