© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21826
    Prev
    Next
    INDEX
    Explanations

    risk-taking, involved, management, sport

    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
    ../../../
    -0.10
    oop
    -0.09
    åİļåİļçļĦ
    -0.09
    常说
    -0.09
    este
    -0.09
    è´¯
    -0.09
    kins
    -0.09
    åİļåİļ
    -0.09
    åŃIJåŃĻ
    -0.09
    agus
    -0.08
    POSITIVE LOGITS
    æķŀ
    0.13
    -taking
    0.11
    lessly
    0.10
    ÑĤан
    0.10
    ified
    0.10
    olta
    0.09
    è¶ĬæĿ¥è¶Ĭ大
    0.09
    è¶Ĭ大
    0.09
    ï¸ı
    0.09
    åľ¨äºİ
    0.09
    Activations Density 0.043%

    No Known Activations