© 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. 2551
    Prev
    Next
    INDEX
    Explanations

    turn direction

    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
    ENN
    -0.24
     Ratings
    -0.23
    ä¹ĭä½Ļ
    -0.23
    éĢıæĺİ
    -0.23
     ratings
    -0.23
    社ä¼ļåĮĸ
    -0.23
    æĻ®éĢļ人
    -0.22
    æİĤ
    -0.22
     suk
    -0.22
    ratings
    -0.22
    POSITIVE LOGITS
     clockwise
    0.30
     zig
    0.30
     west
    0.29
     perpendicular
    0.29
    åIJijä¸ĭ
    0.28
     immediately
    0.28
     inward
    0.28
    /Branch
    0.27
     routes
    0.27
     downward
    0.27
    Activations Density 0.007%

    No Known Activations