© 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. 2098
    Prev
    Next
    INDEX
    Explanations

    account login or usage

    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
    è±ģ
    -0.24
    индивид
    -0.23
    _figure
    -0.22
    oad
    -0.22
     bluff
    -0.21
     grav
    -0.21
    медиÑĨинÑģк
    -0.21
     ÐŁÐ¾Ñĩем
    -0.21
    åı£
    -0.21
     datatype
    -0.20
    POSITIVE LOGITS
    hot
    0.23
    Log
    0.23
    asm
    0.23
    craft
    0.23
    æŀĦæĢĿ
    0.23
    æĭĮ
    0.22
    ru
    0.22
    isu
    0.22
    yy
    0.22
    accounts
    0.22
    Activations Density 0.003%

    No Known Activations