© 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. 2731
    Prev
    Next
    INDEX
    Explanations

    multiple-offer situations

    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
     aqu
    -0.22
     Gamb
    -0.21
     Po
    -0.21
    ?p
    -0.20
     Reviewed
    -0.20
    +s
    -0.20
     po
    -0.20
    .pair
    -0.20
     Confidential
    -0.20
     Cald
    -0.19
    POSITIVE LOGITS
    utive
    0.22
    imations
    0.21
    ä¹ĭéģĵ
    0.21
    æīĢ带æĿ¥çļĦ
    0.20
    ä¹ĭä¸Ĭ
    0.20
    utas
    0.20
    令
    0.20
    çĦ¦èĻij
    0.20
    ycz
    0.20
    edic
    0.20
    Activations Density 0.188%

    No Known Activations