© 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. 55151
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    é£ŀæī¬
    -0.11
    踹
    -0.09
    _CLR
    -0.09
    èŀ¨
    -0.09
    .Dot
    -0.09
    åĺŀ
    -0.09
    ç»Ĩå¿ĥ
    -0.09
    å¾·å°Ķ
    -0.09
    isplay
    -0.09
    imen
    -0.09
    POSITIVE LOGITS
    gow
    0.09
    åĬłæ²¹ç«Ļ
    0.08
    æ¯Ķä¸Ĭå¹´
    0.08
    ombo
    0.08
    åį±
    0.08
    ÙĨ
    0.08
    æľīæīĢ
    0.08
    дон
    0.07
    çĪ°
    0.07
    äºĭå®ŀä¸Ĭ
    0.07
    Activations Density 0.001%

    No Known Activations