© 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. 2077
    Prev
    Next
    INDEX
    Explanations

    dates and ranges

    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
    gee
    -0.21
    'gc
    -0.21
    VML
    -0.21
    LError
    -0.21
     pleasing
    -0.20
    IRO
    -0.20
    éĻĽ
    -0.20
     cara
    -0.20
     menn
    -0.20
     manh
    -0.20
    POSITIVE LOGITS
     onwards
    0.43
    èĩ³
    0.40
     onward
    0.36
    ä¸Ģ缴åĪ°
    0.33
    åĪ°
    0.31
    å¹´èĩ³
    0.31
    èĩ³ä»Ĭ
    0.31
    èµ·æŃ¥
    0.29
    缴èĩ³
    0.29
     until
    0.29
    Activations Density 0.078%

    No Known Activations