© 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. 30587
    Prev
    Next
    INDEX
    Explanations

    missing something or someone

    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
    åħ³æ³¨åº¦
    -0.09
    ä¸Ģ个æĸ°çļĦ
    -0.09
    访
    -0.09
    íį¼
    -0.09
    AILS
    -0.08
    çİ°åľº
    -0.08
    å¿ĥåºķ
    -0.08
    åĪ©çĽĬ
    -0.08
    æĭĽåij¼
    -0.08
    è¡Ģ液
    -0.08
    POSITIVE LOGITS
    ä¸įå·²
    0.14
    ä¹ĭæĥħ
    0.11
    æ¾
    0.09
    åĽ¡
    0.09
    ç§į
    0.09
    лок
    0.08
    èµ·
    0.08
    çĩĶ
    0.08
    ä¸įæŃ¢
    0.08
    è°¯
    0.08
    Activations Density 0.006%

    No Known Activations