© 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. 2618
    Prev
    Next
    INDEX
    Explanations

    also, fellow

    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
    太å°ij
    -0.27
    efa
    -0.24
    bish
    -0.24
    jas
    -0.23
    ajas
    -0.22
    BAB
    -0.22
    _sol
    -0.22
    formation
    -0.22
     realmente
    -0.22
    Åijs
    -0.22
    POSITIVE LOGITS
     equally
    0.30
    åIJĮæł·
    0.30
     similarly
    0.29
    åIJĮ樣
    0.27
    ä¸ĢåIJį
    0.24
    ellig
    0.24
     getState
    0.23
    åīįè¡Į
    0.23
    $type
    0.22
    åĢ¼å¾Ĺåħ³æ³¨
    0.22
    Activations Density 0.109%

    No Known Activations