© 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. 13275
    Prev
    Next
    INDEX
    Explanations

    space, items, or quantity

    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
    ç¾Ķ
    -0.24
     Regional
    -0.21
    çļĵ
    -0.21
     sourceMappingURL
    -0.20
    åİ¥
    -0.19
     Outline
    -0.19
    åı¯éĿłçļĦ
    -0.19
    çįIJ
    -0.19
     regional
    -0.19
     Operator
    -0.19
    POSITIVE LOGITS
    çī©åĵģ
    0.31
    æĶ¶çº³
    0.28
    æķ´çIJĨ
    0.28
    æ¸ħçIJĨ
    0.28
     items
    0.24
    ç¾İåĮĸ
    0.22
     clutter
    0.22
     quantity
    0.22
    æĸ°ä¸ī
    0.21
     storage
    0.21
    Activations Density 0.020%

    No Known Activations