© 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. 3697
    Prev
    Next
    INDEX
    Explanations

    universities and institutions

    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
    æľ
    -0.10
    èŁ¾
    -0.09
     zob
    -0.09
    ä¸įå¦Ĥ
    -0.09
    æĦķ
    -0.09
    åľ¨åĽ½åĨħ
    -0.09
    å¼ŁåħĦ
    -0.08
    è£ģ
    -0.08
    ç§ģä¸ĭ
    -0.08
    querque
    -0.08
    POSITIVE LOGITS
    御
    0.10
    rz
    0.09
     دائ
    0.08
    æĺĬ
    0.08
    estate
    0.08
    æ°¤
    0.08
    å®ľ
    0.08
    rick
    0.08
    ÑıÑĤи
    0.08
    é¾ļ
    0.08
    Activations Density 0.295%

    No Known Activations