© 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. 11006
    Prev
    Next
    INDEX
    Explanations

    life of X or life and X

    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
    åľ¨éĤ£éĩĮ
    -0.12
    åľ¨è¿ĻéĩĮ
    -0.10
    Licensed
    -0.10
    åľ¨è¿Ļ个
    -0.09
    çĽijå¯Ł
    -0.09
    ç¥ī
    -0.09
    ä¾Ľç»Ļ侧
    -0.09
    canf
    -0.09
     Rays
    -0.09
    éĹ¼
    -0.09
    POSITIVE LOGITS
    èĻ½
    0.08
    heard
    0.08
    åıªåī©ä¸ĭ
    0.08
    nad
    0.08
     cad
    0.08
    横
    0.08
     кÑĢай
    0.07
    iamond
    0.07
    CTX
    0.07
    åIJĪèµĦåħ¬åı¸
    0.07
    Activations Density 0.027%

    No Known Activations