© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14878
    Prev
    Next
    INDEX
    Explanations

    distance between or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æĹ¶æ®µ
    -0.19
    ä¸įæĪIJ
    -0.18
    wald
    -0.18
     appName
    -0.18
    ç¼´
    -0.18
    è¡İ
    -0.18
    pictured
    -0.17
    ả
    -0.17
    utherland
    -0.17
    çķĻåŃĺ
    -0.17
    POSITIVE LOGITS
    è·Ŀ离
    0.40
     distance
    0.36
    çļĦè·Ŀ离
    0.36
    è·ĿéĽ¢
    0.35
     Distance
    0.35
    Distance
    0.34
     distances
    0.31
    distance
    0.31
    (distance
    0.31
    _distance
    0.30
    Activations Density 0.050%

    No Known Activations