© 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. 53404
    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
    æµ·åŁŁ
    -0.09
     Fauc
    -0.09
    åIJŁ
    -0.08
    æĬł
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    ä¸ĢæĬĬ
    -0.08
    åijĺ
    -0.08
    ç¿Ģ
    -0.08
    è´©åįĸ
    -0.08
    裸
    -0.08
    POSITIVE LOGITS
    æ±ŁåįĹ
    0.10
    _boolean
    0.09
    æ¾Ħæ¸ħ
    0.09
    çĪ°
    0.09
    Boolean
    0.09
    olumn
    0.09
    çĥ¦
    0.09
    otime
    0.08
    _BOOLEAN
    0.08
    oland
    0.08
    Activations Density 0.034%

    No Known Activations