© 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. 1679
    Prev
    Next
    INDEX
    Explanations

    strategy or game with board, warfare, or generals

    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
     taped
    -0.29
     stamped
    -0.29
    è¡Ĺ头
    -0.26
    æĮīæij©
    -0.26
    æĮĤçīĮ
    -0.25
    亮
    -0.25
    çĻ½è¡£
    -0.25
     sidewalk
    -0.25
    注å°Ħ
    -0.25
    è¡Ĺä¸Ĭ
    -0.25
    POSITIVE LOGITS
    æĪĺäºī
    0.39
     warfare
    0.39
    สà¸ĩà¸Ħราม
    0.36
     generals
    0.36
    åħµåĬĽ
    0.35
    èĥľè´Ł
    0.35
    åĨĽäºĭ
    0.35
    åįļå¼Ī
    0.34
    æĪĺçķ¥
    0.34
    æĪĺåľº
    0.33
    Activations Density 0.053%

    No Known Activations