© 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. 3175
    Prev
    Next
    INDEX
    Explanations

    probability of picking from list

    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
    Negative Logits
    ç¥Ģ
    -0.27
     cate
    -0.23
    KD
    -0.23
    ACCEPT
    -0.23
     pilgrimage
    -0.22
    irl
    -0.22
    izi
    -0.22
    åīįæĿ¥
    -0.22
    (Unknown
    -0.22
    ä¸Ģè¶Ł
    -0.22
    POSITIVE LOGITS
    antine
    0.22
    ArgumentException
    0.22
    erial
    0.21
    ulos
    0.21
     fract
    0.20
    ('-',
    0.20
     ICollection
    0.20
    æĸ°å½¢åĬ¿ä¸ĭ
    0.20
    GPL
    0.20
    åºij
    0.20
    Activations Density 0.003%

    No Known Activations