© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2244
    Prev
    Next
    INDEX
    Explanations

    crime, questions, and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    笺
    -0.24
    ÑĮе
    -0.23
    vari
    -0.22
    lus
    -0.22
    ฯ
    -0.21
    elib
    -0.21
     crochet
    -0.21
    -inst
    -0.21
    cep
    -0.21
    èĢģçĻ¾å§ĵ
    -0.21
    POSITIVE LOGITS
     Zuk
    0.23
    ĵĺ
    0.22
    转åŀĭ
    0.22
    ç¡¿
    0.21
    çļĦåĨ³å¿ĥ
    0.21
    ìłij
    0.20
    æļħ
    0.20
    æ¼ıæ°´
    0.20
    obox
    0.20
    åįıä¼ļä¼ļéķ¿
    0.20
    Activations Density 0.002%

    No Known Activations