© 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. 10982
    Prev
    Next
    INDEX
    Explanations

    issue or -button

    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
    óc
    -0.09
    éķ¿çŁŃ
    -0.09
    astle
    -0.09
    ourcem
    -0.09
    á¿ĸ
    -0.09
    ission
    -0.08
    _xpath
    -0.08
    åı²ä¸ĬæľĢ
    -0.08
    æĥ³åĥı
    -0.08
    å¾Ģå¹´
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.14
    ä¸Ģç¬Ķ
    0.12
    edly
    0.12
    å¼ıçļĦ
    0.11
    èĪ¬
    0.11
    å±ĢéĿ¢
    0.10
    ela
    0.09
    ä¸Ģæī¹
    0.09
    é¹Ń
    0.09
    ä¼¼çļĦ
    0.09
    Activations Density 0.093%

    No Known Activations