© 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. 39920
    Prev
    Next
    INDEX
    Explanations

    essential for survival

    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
    éĺĬ
    -0.11
    åıĪ好
    -0.11
    ä¸įåħį
    -0.11
    帷
    -0.11
    åĪĩåħ¥
    -0.11
    è¿ĺè®°å¾Ĺ
    -0.10
    é²¢
    -0.10
    å¸ı
    -0.10
    afil
    -0.10
    裸
    -0.10
    POSITIVE LOGITS
    就没æľī
    0.10
    .fm
    0.09
    ä¸įè¡Į
    0.09
    azu
    0.08
     pine
    0.08
    sass
    0.08
    ä¸įäºĨ
    0.08
    çļĦ話
    0.08
    èĬĤ
    0.08
     Shed
    0.07
    Activations Density 0.044%

    No Known Activations