© 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. 23022
    Prev
    Next
    INDEX
    Explanations

    how to explanation

    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
    被æĬĵ
    -0.10
    åĹª
    -0.09
    /sc
    -0.09
    8
    -0.09
    6
    -0.09
    缯
    -0.08
    brush
    -0.08
    5
    -0.08
    秽
    -0.08
    人æĿĥ
    -0.08
    POSITIVE LOGITS
    æ´¾
    0.10
    åħ±åIJĮåĬªåĬĽ
    0.10
    çľģéĴ±
    0.10
    éĿĵ
    0.10
    æľĢ大åĮĸ
    0.09
    ç»ĨåĪĻ
    0.09
    箪
    0.09
     поможеÑĤ
    0.09
    çī¹åĪ«æĺ¯åľ¨
    0.08
    .CopyTo
    0.08
    Activations Density 0.029%

    No Known Activations