© 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. 61817
    Prev
    Next
    INDEX
    Explanations

    precaution, case, sure, warranted

    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
    æµ´
    -0.09
    羡æħķ
    -0.09
    dry
    -0.09
    å¹²
    -0.08
    ucha
    -0.08
     ÑĢеÑģÑĤ
    -0.08
    HS
    -0.08
     Lob
    -0.08
    //=
    -0.08
    缸åıį
    -0.08
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.16
    æĭħå¿ĥ
    0.12
    ä¿ĿéĻ©
    0.11
    稳妥
    0.11
     precaution
    0.11
    æĭħ忧
    0.10
    æĽ´ä½ķåĨµ
    0.10
    æĿŀ
    0.10
    åĩºäºİ
    0.10
    ä¿Ŀå®Ī
    0.10
    Activations Density 0.081%

    No Known Activations