© 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. 29689
    Prev
    Next
    INDEX
    Explanations

    terminal input

    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
    éĻ¶çĵ·
    -0.10
    reff
    -0.09
    åĪ»
    -0.09
    éĩĮç¨ĭç¢ij
    -0.09
    è·ijåĪ°
    -0.09
    acci
    -0.09
    æĿŀ
    -0.09
    çŃĭ
    -0.09
    æľ¬åij¨
    -0.09
    åĬ¨æīĭ
    -0.09
    POSITIVE LOGITS
    terminal
    0.11
     terminal
    0.11
    ç»Ī端
    0.11
    _terminal
    0.10
    è¾ĵåħ¥
    0.09
     input
    0.09
    tty
    0.09
     interactive
    0.09
    çŃĶ
    0.09
     Terminal
    0.09
    Activations Density 0.395%

    No Known Activations