© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63917
    Prev
    Next
    INDEX
    Explanations

    approximate / approximation

    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
    Negative Logits
    è¶Ĭå¤ļ
    -0.10
    éħ·
    -0.10
    èĹIJ
    -0.10
    ROKE
    -0.10
    åĴĮåľ°åĮº
    -0.09
    é¢ĦåĶ®
    -0.09
     Hav
    -0.09
    åı¨
    -0.09
    æ±Ľ
    -0.09
    è¿ĺä¸įå¤Ł
    -0.09
    POSITIVE LOGITS
    imations
    0.13
    imate
    0.12
    imating
    0.11
    ateur
    0.09
    gle
    0.09
    imated
    0.09
    iy
    0.09
    uary
    0.09
    adamente
    0.09
    è°Īè°Ī
    0.09
    Activations Density 0.028%

    No Known Activations