© 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. 11289
    Prev
    Next
    INDEX
    Explanations

    included patients

    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
    è¡Įæĥħ
    -0.10
    unal
    -0.09
    åĬ©åѦ
    -0.09
    onom
    -0.08
    åĩ¤
    -0.08
     Alley
    -0.08
    è¹Ī
    -0.08
    ç¡®
    -0.08
     trophy
    -0.08
     полÑĥÑĩениÑı
    -0.08
    POSITIVE LOGITS
    cases
    0.10
    è¿ĽæĿ¥
    0.10
    毫ä¸įçĬ¹è±«
    0.10
    符åIJĪæĿ¡ä»¶
    0.10
    éĩįä¸Ń
    0.09
    æł·æľ¬
    0.09
    çĹħä¾ĭ
    0.09
    人éĢī
    0.09
    éĢĦ
    0.09
    ering
    0.08
    Activations Density 0.842%

    No Known Activations