© 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. 1079
    Prev
    Next
    INDEX
    Explanations

    authors and their works

    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
    绺
    -0.09
    é²ł
    -0.09
    ABEL
    -0.09
    å¿«æĬ¥
    -0.09
    å¸ĸ
    -0.09
    æ·±æĥħ
    -0.09
    æĴŃæĬ¥
    -0.08
    ãĥ¬ãĥĵãĥ¥ãĥ¼
    -0.08
    éĤ®ç®±
    -0.08
     Primitive
    -0.08
    POSITIVE LOGITS
    å¿į
    0.10
     himself
    0.08
    à¹Ħà¸ĭ
    0.08
    æĹ¥æľ¬äºº
    0.08
    èĻIJ
    0.08
    社
    0.08
    大å¸Ī
    0.08
     guy
    0.08
     Taxi
    0.07
     intervening
    0.07
    Activations Density 0.027%

    No Known Activations