© 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. 49830
    Prev
    Next
    INDEX
    Explanations

    suitable 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
    aceous
    -0.11
    наÑĤ
    -0.09
    al
    -0.09
    ÄĻ
    -0.09
    Ùī
    -0.08
    panic
    -0.08
    r
    -0.08
    á»įng
    -0.08
    ing
    -0.08
    æł·åŃIJ
    -0.08
    POSITIVE LOGITS
    åĽ½æĥħ
    0.10
    ä¸įåłª
    0.10
    brains
    0.10
    NESS
    0.10
    çļĦåŃ¦ä¹ł
    0.10
    ä¸įéĢĤåIJĪ
    0.10
    -sized
    0.09
    ç¿ķ
    0.09
    oop
    0.09
    iten
    0.09
    Activations Density 0.020%

    No Known Activations