© 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. 1958
    Prev
    Next
    INDEX
    Explanations

    Bangladesh

    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
    linger
    -0.24
    ached
    -0.22
    æĢľ
    -0.21
    flo
    -0.20
    listen
    -0.20
    cle
    -0.20
    rometer
    -0.20
    åĴĮæĬĢæľ¯
    -0.20
    untas
    -0.20
    nom
    -0.20
    POSITIVE LOGITS
     coarse
    0.21
     DVD
    0.21
     Br
    0.21
    ÅĤo
    0.21
    DK
    0.20
    ged
    0.20
    /New
    0.20
    /Z
    0.20
     TV
    0.19
    -New
    0.19
    Activations Density 0.005%

    No Known Activations