© 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. 14860
    Prev
    Next
    INDEX
    Explanations

    positive connotations

    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
    éĤ£ç§į
    -0.23
    èĢĨ
    -0.20
    çļĦä¸ĢäºĽ
    -0.20
    itzer
    -0.20
    ä¸ĢäºĽ
    -0.19
    ä¸Ģåī¯
    -0.19
     dotyczÄħce
    -0.19
     Fresh
    -0.19
    way
    -0.18
    rier
    -0.18
    POSITIVE LOGITS
    åij½åIJį为
    0.21
    æĤī
    0.21
    çļĦ大
    0.20
    ç¾İ好çĶŁæ´»
    0.20
    ->__
    0.19
    /classes
    0.19
    mma
    0.19
    çļĦèĢģ
    0.18
    æ¡©
    0.18
     absol
    0.17
    Activations Density 0.490%

    No Known Activations