© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1003
    Prev
    Next
    INDEX
    Explanations

    forwarded by Enron/ECT

    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
    пÑĥÑĤ
    -0.27
    .bs
    -0.23
    DOC
    -0.23
    ius
    -0.22
    å«£
    -0.22
    ;]/
    -0.21
    ient
    -0.21
    thumbs
    -0.21
     molt
    -0.21
    enus
    -0.21
    POSITIVE LOGITS
    羸
    0.24
    èµ¢
    0.24
    è°ģèĥ½
    0.22
    endale
    0.22
    vil
    0.22
    uyo
    0.22
    dw
    0.22
    Ĺı
    0.22
     COMPUT
    0.21
     REPL
    0.21
    Activations Density 0.302%

    No Known Activations