© 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. 16908
    Prev
    Next
    INDEX
    Explanations

    puzzle or question solving

    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
    _MIX
    -0.21
    REFERENCES
    -0.20
    steder
    -0.19
    ucher
    -0.19
     runApp
    -0.19
    æ·±åħ¥äºĨ解
    -0.19
    .beh
    -0.19
    æ¯ıéļĶ
    -0.18
    缮çļĦåľ¨äºİ
    -0.18
    =create
    -0.18
    POSITIVE LOGITS
    çŃĶé¢ĺ
    0.38
    çĮľ
    0.32
    çŃĶ
    0.29
    æŃ£ç¡®
    0.28
    å¾ĹåĪĨ
    0.27
    èĩªä¿¡
    0.26
    é¢ĺ
    0.26
    è¿ĩåħ³
    0.25
    解çŃĶ
    0.25
    æĢĿè·¯
    0.25
    Activations Density 0.034%

    No Known Activations