© 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. 1768
    Prev
    Next
    INDEX
    Explanations

    Stack Exchange or Stack Overflow

    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
    管çIJĨå±Ĥ
    -0.25
    å¨Ī
    -0.24
    agi
    -0.24
     emailAddress
    -0.24
     cad
    -0.23
    /cgi
    -0.23
    ä¸įåı¯ç¼ºå°ij
    -0.23
    addChild
    -0.23
    cba
    -0.23
    LBL
    -0.23
    POSITIVE LOGITS
    çŁ¥ä¹İ
    0.39
     Stack
    0.35
     answered
    0.34
    éĹ®çŃĶ
    0.33
     GitHub
    0.32
    Stack
    0.32
     bounty
    0.32
    -answer
    0.32
     Asking
    0.32
    TeX
    0.31
    Activations Density 0.441%

    No Known Activations