© 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. 57225
    Prev
    Next
    INDEX
    Explanations

    during specific times

    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
    _NOP
    -0.10
    ä¸Ńæĸ°
    -0.10
    arters
    -0.09
    缸èģļ
    -0.09
    æľ±
    -0.09
    éģĩéļ¾
    -0.09
    æĺİæĹ¥
    -0.09
    ìĪĻ
    -0.09
    座
    -0.09
    å±ŀå®ŀ
    -0.09
    POSITIVE LOGITS
    è¿ĺ好
    0.09
    ambre
    0.08
    æľĢåħ³éĶ®çļĦ
    0.08
    ä»°
    0.08
    æĪĺäºī
    0.08
    ç«
    0.07
    ä¸ĢçĽ´æ²¡æľī
    0.07
    天çĦ¶
    0.07
    æļĩ
    0.07
     Globe
    0.07
    Activations Density 0.031%

    No Known Activations