© 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. 38884
    Prev
    Next
    INDEX
    Explanations

    directions, driving, routes

    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
    ä¹ĺ
    -0.10
    汽车
    -0.10
    ä¸ŃåĽ½æ±½è½¦
    -0.10
    èĩªè¡Į车
    -0.10
    çĶ¨è½¦
    -0.10
    è¢ľ
    -0.09
    éģ©çĶ¨
    -0.09
    лей
    -0.08
    éħ©
    -0.08
     reuse
    -0.08
    POSITIVE LOGITS
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.09
    çģ«çĦ°
    0.09
    éĹª
    0.09
    edy
    0.09
     ÑģÑĤоÑĢ
    0.09
    æĬ¥
    0.08
    ÑĪей
    0.08
    èĻĽ
    0.08
    æ¥Ķ
    0.08
    RITE
    0.08
    Activations Density 0.092%

    No Known Activations