© 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. 54997
    Prev
    Next
    INDEX
    Explanations

    impending danger or threat

    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
     Anc
    -0.09
    éĻĨç»Ń
    -0.09
    fight
    -0.08
    grass
    -0.08
    ä¸įéĢļ
    -0.08
    è¾£
    -0.08
    girl
    -0.08
    åŃ£
    -0.08
    olini
    -0.08
    ç³Łç³ķ
    -0.08
    POSITIVE LOGITS
    ingly
    0.10
    éĺ´å½±
    0.10
    æĮ¥
    0.10
    åĽĽåij¨
    0.09
    踪
    0.09
    PIP
    0.09
    æĢł
    0.09
     nhắc
    0.09
    ูà¹Ī
    0.09
    rub
    0.09
    Activations Density 0.013%

    No Known Activations