© 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. 2404
    Prev
    Next
    INDEX
    Explanations

    invitation to join or visit

    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
    ä¸Ģ级
    -0.26
    CUS
    -0.26
    ä¼łå¥ĩ
    -0.23
    ocr
    -0.23
    强æľīåĬĽçļĦ
    -0.22
    PLAYER
    -0.22
    variant
    -0.22
    olini
    -0.21
    æİĴåĪĹ
    -0.21
    æĦıåij³çĿĢ
    -0.21
    POSITIVE LOGITS
     join
    0.28
     leisure
    0.27
     anytime
    0.27
     visit
    0.26
     regardless
    0.26
     Join
    0.25
    éļıæĦı
    0.25
     camar
    0.25
    (join
    0.25
    Join
    0.25
    Activations Density 0.016%

    No Known Activations