© 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. 3082
    Prev
    Next
    INDEX
    Explanations

    Mail Online

    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
    NSNotificationCenter
    -0.23
    ç±ģ
    -0.23
    aaS
    -0.22
    DataContext
    -0.22
    <typeof
    -0.22
    æł¸
    -0.22
     OID
    -0.22
    che
    -0.21
    顺
    -0.21
    (forKey
    -0.21
    POSITIVE LOGITS
     Scroll
    0.26
    æıŃç§ĺ
    0.26
    -esque
    0.24
     shocking
    0.23
    IJľ
    0.23
    èĿ´èĿ¶
    0.23
     Doctors
    0.22
     COLUMN
    0.22
     Arabian
    0.22
    estate
    0.22
    Activations Density 0.044%

    No Known Activations