© 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. 11558
    Prev
    Next
    INDEX
    Explanations

    spatial position or progress

    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
    éģįåıĬ
    -0.09
    æĬ¢åħĪ
    -0.09
    éĻ·åħ¥
    -0.08
    æīĢåľ¨åľ°
    -0.08
    æľ¬èº«çļĦ
    -0.08
    åĸĦæĦı
    -0.08
    NIL
    -0.08
    جÙĨ
    -0.08
    秤
    -0.08
    ç»ı纬
    -0.08
    POSITIVE LOGITS
    UTILITY
    0.10
    æĿ¥çļĦ
    0.09
    å¸IJ
    0.09
    è§Ī
    0.09
    rek
    0.08
     Probe
    0.08
    æݨå¼Ģ
    0.08
    è·ĿéĽ¢
    0.08
    è¿ĩæĿ¥
    0.08
    ilers
    0.08
    Activations Density 0.070%

    No Known Activations