© 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. 56546
    Prev
    Next
    INDEX
    Explanations

    root

    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
    æªIJ
    -0.11
    ä¸įåŃķ
    -0.10
    èŁij
    -0.10
    isers
    -0.10
    éĻĨ
    -0.10
    ppy
    -0.09
    é³¥
    -0.09
    AIT
    -0.09
    ixel
    -0.09
    鸣
    -0.09
    POSITIVE LOGITS
    æł¹
    0.10
    éĥ¨éķ¿
    0.09
     Garland
    0.09
    èIJĿåįľ
    0.09
     root
    0.09
    çģµéŃĤ
    0.09
    èį¸
    0.09
    æ¶İ
    0.09
     digs
    0.08
    igers
    0.08
    Activations Density 0.062%

    No Known Activations