© 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. 58903
    Prev
    Next
    INDEX
    Explanations

    devote / dedicate

    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
    vier
    -0.11
     TILE
    -0.10
    çĭ¬è§Ĵåħ½
    -0.10
    лик
    -0.09
    å§ĭç»Īä¿ĿæĮģ
    -0.09
    æĬĵç´§
    -0.09
    è£ĺ
    -0.09
    .Timestamp
    -0.09
    å¼Ģå¿ĥ
    -0.09
    ä¸įåľ¨
    -0.09
    POSITIVE LOGITS
    ãģĤãĤĭç¨ĭ度
    0.10
    ä¸Ģå®ļçļĦ
    0.10
    缸å½ĵ
    0.09
    ç²¾åĬĽ
    0.09
    boo
    0.08
     меÑģÑĤо
    0.08
    æķ´ä¸ª
    0.08
    å»Ĭ
    0.08
    éķ¿èĢģ
    0.08
    å§ij
    0.08
    Activations Density 0.015%

    No Known Activations