© 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. 12142
    Prev
    Next
    INDEX
    Explanations

    fuel delivery and usage

    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
    ngen
    -0.09
    åĢ¦
    -0.09
    åŀĤ
    -0.09
    ç¿İ
    -0.09
    æĶ¾æīĭ
    -0.09
    _SENS
    -0.09
    _ELEMENTS
    -0.09
    éªŀ
    -0.09
    第ä¸Ģéĥ¨
    -0.09
    å¿«éĢŁåıijå±ķ
    -0.08
    POSITIVE LOGITS
    åĽ¤
    0.11
    æ½®
    0.09
    onus
    0.09
    สà¸Ķ
    0.09
    åĨį说
    0.08
    ابر
    0.08
    åĤ¨å¤ĩ
    0.08
    å®ļæľŁ
    0.08
    循
    0.08
    ä¾ĽåºĶ
    0.08
    Activations Density 0.065%

    No Known Activations