© 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. 3027
    Prev
    Next
    INDEX
    Explanations

    parts of words

    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
    主æĿĥ
    -0.27
    uffers
    -0.27
    èĩªåĪ¶
    -0.23
    eterminate
    -0.22
    eken
    -0.22
     ///<
    -0.21
    æ®Ĭ
    -0.21
     huh
    -0.21
    TypeInfo
    -0.21
    coes
    -0.21
    POSITIVE LOGITS
    æĥħåĨµæĿ¥çľĭ
    0.26
     Married
    0.25
    existing
    0.25
     Girlfriend
    0.24
     Supporting
    0.24
    arger
    0.23
    mentioned
    0.23
    portun
    0.23
     oldest
    0.22
    ð«Ĺ
    0.22
    Activations Density 0.027%

    No Known Activations