© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    login or register

    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
    /arch
    -0.24
    åĴĮæĬĢæľ¯
    -0.23
    retty
    -0.22
    以åıĬ
    -0.22
    YLON
    -0.22
    æ½ľèĥ½
    -0.22
    Łèĥ½
    -0.21
     compan
    -0.21
    prm
    -0.21
    GINE
    -0.21
    POSITIVE LOGITS
    注æĺİæĿ¥æºIJ
    0.25
    æıIJåıĸ
    0.23
    å¨Ħ
    0.23
    注
    0.23
     obs
    0.23
     Tol
    0.23
    odom
    0.23
    ator
    0.22
     Bus
    0.22
    l
    0.22
    Activations Density 0.010%

    No Known Activations