© 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. 9019
    Prev
    Next
    INDEX
    Explanations

    code import or comments

    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
    -0.08
     wiki
    -0.08
    åĸĨ
    -0.08
    è¾ĩ
    -0.08
    åı¯èĥ½åıijçĶŁ
    -0.08
    ×Ļ×Ŀ
    -0.08
    apolis
    -0.08
     .
    -0.07
    indic
    -0.07
    è¯ģ
    -0.07
    POSITIVE LOGITS
    lage
    0.10
    ASY
    0.09
    ç©¿è¡£
    0.09
     поÑģколÑĮ
    0.09
    åĮĸçļĦ
    0.09
    æĸ°çļĦä¸Ģ
    0.09
    éĤķ
    0.09
    bro
    0.09
    agements
    0.09
    æ¡Ģ
    0.09
    Activations Density 0.229%

    No Known Activations