© 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. 409
    Prev
    Next
    INDEX
    Explanations

    attorney, examiner, sheriff, engineers

    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
    ä¸ŃåĽ½çī¹èī²
    -0.25
     Manifest
    -0.23
    onis
    -0.23
    Editors
    -0.22
    OrCreate
    -0.21
     thiá»ĥu
    -0.21
     seeds
    -0.21
    (keys
    -0.20
    _INCLUDE
    -0.20
    .NewReader
    -0.20
    POSITIVE LOGITS
    åģļå®Į
    0.24
    ä¸Ĭåı¸
    0.24
    çĤ³
    0.24
     department
    0.23
    认å®ļ
    0.23
     bureau
    0.23
     periodically
    0.22
    kre
    0.22
    认åı¯
    0.22
    ulla
    0.22
    Activations Density 0.003%

    No Known Activations