© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    code, foreign languages

    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
     college
    -0.28
     employees
    -0.27
     Office
    -0.26
    èģĮå·¥
    -0.26
     programs
    -0.25
    诸å¦Ĥ
    -0.25
     someday
    -0.25
     director
    -0.25
    éĺ²èħIJ
    -0.25
     faculty
    -0.24
    POSITIVE LOGITS
    è§ĴéĢIJ
    0.33
    è·¯åĨµ
    0.33
    第ä¸ĢåIJį
    0.32
    åĩıéĢŁ
    0.32
     competitors
    0.31
    ç«ŀäºī
    0.31
    æıIJéĢŁ
    0.30
     competitor
    0.30
    atedRoute
    0.29
    äºļåĨĽ
    0.29
    Activations Density 0.027%

    No Known Activations