© 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. 39546
    Prev
    Next
    INDEX
    Explanations

    reason for that

    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
    å¿«æĿ¥
    -0.10
    åĽĽæĸ¹
    -0.09
    çĶŁäº§æĢ»
    -0.08
    åIJ®
    -0.08
     ker
    -0.08
    оÑĩки
    -0.08
    æľīæķĪåľ°
    -0.08
    è´¡
    -0.08
    Ñģком
    -0.08
     Ker
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪĩ
    0.13
    æĺ¯åĽłä¸º
    0.11
     reason
    0.11
    çļĦåİŁåĽł
    0.10
    çŁ¥éģĵ
    0.10
    ä¹ĭæīĢ以
    0.09
     Polo
    0.09
    reason
    0.09
    è¿Ļ
    0.09
    éĥ¡
    0.09
    Activations Density 0.017%

    No Known Activations