© 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. 11857
    Prev
    Next
    INDEX
    Explanations

    cite citations

    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
    æĭ¼
    -0.18
    å¤ĸéĿ¢
    -0.18
    asso
    -0.18
     Erotische
    -0.17
    å¸ĥ
    -0.17
    aux
    -0.17
     ÅļwiÄĻt
    -0.17
    ä½
    -0.17
    è·Ł
    -0.17
     Geile
    -0.17
    POSITIVE LOGITS
    è¿Ļä¹Łæĺ¯
    0.22
    详è§ģ
    0.21
    黩
    0.20
    ãĥ£
    0.20
    æīĢ以说
    0.19
     []).
    0.18
    æ¯Ķå¦Ĥ说
    0.18
    åįİ侨
    0.17
    ä¾ĭå¦Ĥ
    0.17
    è¿Ļå°±
    0.17
    Activations Density 0.204%

    No Known Activations