© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3107
    Prev
    Next
    INDEX
    Explanations

    which X, when to, who can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ä¸Ģç»ı
    -0.25
    ç¡®ä¿Ŀ
    -0.24
    åı¯æĥ³èĢĮçŁ¥
    -0.22
    设æĥ³
    -0.21
    æķĪæŀľåĽ¾
    -0.21
    _ENT
    -0.21
    probably
    -0.21
     gab
    -0.20
    aison
    -0.20
     Minds
    -0.20
    POSITIVE LOGITS
    /how
    0.41
    æł·çļĦ
    0.29
    ermann
    0.26
    åĵªäºĽ
    0.25
    wg
    0.24
     beste
    0.24
     basis
    0.24
    éĢĤåIJĪèĩªå·±
    0.23
     constitutes
    0.23
    czas
    0.23
    Activations Density 0.074%

    No Known Activations