© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    dot plots

    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
     воÑĤ
    -0.22
    ADING
    -0.21
    AYS
    -0.20
    hold
    -0.20
    ISTR
    -0.18
    UCH
    -0.18
    ió
    -0.18
    éĤ¸
    -0.18
    IBE
    -0.18
    ording
    -0.18
    POSITIVE LOGITS
    ting
    0.31
    ter
    0.26
    åĦ¿
    0.25
    wise
    0.21
    glob
    0.21
    e
    0.21
    åŃIJéĩĮ
    0.21
    çĿĽ
    0.21
    phere
    0.21
     Peb
    0.21
    Activations Density 0.018%

    No Known Activations