© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2443
    Prev
    Next
    INDEX
    Explanations

    stakeholders, parties, actors

    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
    idious
    -0.23
     depreciation
    -0.21
     tonic
    -0.21
    -click
    -0.20
    åºı
    -0.20
    OfMonth
    -0.20
    umbing
    -0.20
    水管
    -0.20
    ioneer
    -0.20
    setId
    -0.20
    POSITIVE LOGITS
    人士
    0.35
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.30
    åIJĦæĸ¹
    0.30
     interests
    0.27
    hip
    0.27
    æĦŁåħ´è¶£çļĦ
    0.27
    åIJĦ个æĸ¹éĿ¢
    0.26
    åIJĦæĸ¹éĿ¢
    0.24
    èĻij
    0.24
    lor
    0.23
    Activations Density 0.007%

    No Known Activations