© 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. 38734
    Prev
    Next
    INDEX
    Explanations

    in the way

    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
    olls
    -0.11
     беÑģ
    -0.10
    _locals
    -0.10
    å¤ĩçĶ¨
    -0.09
    reserved
    -0.09
    åĩłç§į
    -0.09
    å¤ĩ
    -0.09
    ä¸ŃåĽ½å¤§éĻĨ
    -0.09
    atoria
    -0.09
    ç½ķè§ģ
    -0.09
    POSITIVE LOGITS
    éĺ»ç¢į
    0.22
    妨ç¢į
    0.17
    éĺ»æŃ¢
    0.15
    éļľç¢į
    0.14
    éĻIJåĪ¶
    0.14
     imped
    0.14
    åĪ¶çº¦
    0.14
    éĺ»
    0.13
     hind
    0.13
    éĺ»æĮ¡
    0.13
    Activations Density 0.114%

    No Known Activations