© 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. 27123
    Prev
    Next
    INDEX
    Explanations

    talks or discussions

    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
    heimer
    -0.09
     Morm
    -0.09
    isten
    -0.09
    hop
    -0.08
    çĻ
    -0.08
    趴
    -0.08
    uur
    -0.08
    éĤĿ
    -0.08
    èĢ»
    -0.08
    纽
    -0.08
    POSITIVE LOGITS
    æ»ķ
    0.10
    REP
    0.09
    ä¸į代表
    0.09
    agen
    0.09
     hast
    0.08
     кваÑĢÑĤиÑĢ
    0.08
     Äijâu
    0.08
    ç¡®
    0.08
    è¨Ĺ
    0.08
    atab
    0.08
    Activations Density 0.041%

    No Known Activations