© 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. 49921
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    overs
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.08
    æĢİä¹Ī说
    -0.08
    迹
    -0.08
     elles
    -0.08
    å¤§åľ°
    -0.08
    ä¸įèĪį
    -0.08
    åīIJ
    -0.08
    bull
    -0.08
    å°±çŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    rac
    0.09
    asher
    0.09
    .clean
    0.09
    æĿĤ
    0.09
    uraa
    0.09
    ç»Ĵ
    0.09
    .uf
    0.08
    鼶è·Ŀ离
    0.08
    odzi
    0.08
    çıł
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.