© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 771
    Prev
    Next
    INDEX
    Explanations

    this study song data track

    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
    马ä¸Ĭ
    -0.26
     silence
    -0.24
    FO
    -0.24
    ç»ı常
    -0.23
    úb
    -0.22
     immediately
    -0.22
    å¾Īå¿«
    -0.22
    ç«ĭåį³
    -0.22
    izable
    -0.22
    if
    -0.21
    POSITIVE LOGITS
    æľĢåĪĿçļĦ
    0.28
    è¿Ļä¸ĢåĪĩ
    0.27
     slee
    0.26
     originally
    0.25
    æľĢåĪĿ
    0.24
     Theft
    0.23
    è¿Ļæł·ä¸Ģ
    0.22
    —who
    0.22
    æľĢæĹ©çļĦ
    0.22
    :],
    0.22
    Activations Density 0.135%

    No Known Activations