© 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. 16632
    Prev
    Next
    INDEX
    Explanations

    put on, put in, made available, put 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
    èĩªå·±åĸľæ¬¢
    -0.22
    äºĽä»Ģä¹Ī
    -0.19
    èĩªå·±
    -0.18
    缮åħī
    -0.18
    éĤ£äºĽ
    -0.18
    èĩªå·±çļĦ
    -0.18
    çļĦ缮åħī
    -0.17
    è°ģçŁ¥éģĵ
    -0.17
    åĺ´å·´
    -0.17
    åIJİéĿ¢çļĦ
    -0.17
    POSITIVE LOGITS
    ç¯ĩ
    0.19
    éĻĢ
    0.18
    纳åħ¥
    0.18
    çIJ¢
    0.18
    Æ°
    0.18
    anela
    0.17
    osa
    0.17
    éĢģå¾Ģ
    0.17
     orbit
    0.17
    å±ķ
    0.17
    Activations Density 0.054%

    No Known Activations