© 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. 57867
    Prev
    Next
    INDEX
    Explanations

    questions starting with "how"

    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
    æŀĦæĪIJ
    -0.09
    èĬ¥
    -0.09
    /from
    -0.08
    夤
    -0.08
    олов
    -0.08
    åĽŀäºĭ
    -0.08
    lobs
    -0.08
     полов
    -0.08
    人æµģ
    -0.08
     PROP
    -0.08
    POSITIVE LOGITS
    缴èIJ¥
    0.09
    è¶Ĭæĺ¯
    0.09
    æĽ´èĥ½
    0.09
    Òij
    0.09
    yna
    0.08
    毳
    0.08
    è´«åĽ°æĿij
    0.08
    лиÑģÑĤ
    0.08
     cÃłng
    0.08
    æĦĪ
    0.08
    Activations Density 0.029%

    No Known Activations