© 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. 11488
    Prev
    Next
    INDEX
    Explanations

    disable, delete, change, or read

    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
    åħ»
    -0.21
    nob
    -0.20
     trav
    -0.20
    èįī
    -0.20
     load
    -0.20
    åķĨä¼ļ
    -0.19
    åIJĦè¡ĮåIJĦä¸ļ
    -0.19
    åħ¨ç¤¾ä¼ļ
    -0.19
    ç»´æĮģ
    -0.19
    Phrase
    -0.18
    POSITIVE LOGITS
    ýt
    0.22
    红æĹĹ
    0.20
    çļĦæĿĥåĪ©
    0.20
    èħ´
    0.20
     ê¶Į리
    0.20
    æ¼Ķä¹ł
    0.19
    Terminate
    0.19
    çĹ¿
    0.19
    æķ°æį®ä¸Ńå¿ĥ
    0.19
    _TERMIN
    0.18
    Activations Density 0.027%

    No Known Activations