© 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. 12739
    Prev
    Next
    INDEX
    Explanations

    email address

    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
    ä¸Ģ人
    -0.21
    ideon
    -0.19
    EMA
    -0.19
    ани
    -0.19
    è·
    -0.18
    TM
    -0.18
    Assertions
    -0.18
    OfType
    -0.18
     Revision
    -0.18
     revision
    -0.18
    POSITIVE LOGITS
    éģ¿å¼Ģ
    0.32
    åĽŀéģ¿
    0.28
    éģ¿
    0.26
    éĹ´æİ¥
    0.26
     banned
    0.26
     forbidden
    0.26
    åıĹéĻIJ
    0.25
    æļĹ示
    0.25
    éļĶçĿĢ
    0.25
    躲éģ¿
    0.24
    Activations Density 0.237%

    No Known Activations