© 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. 2952
    Prev
    Next
    INDEX
    Explanations

    path separators followed by words

    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
    å±¥è¡Į
    -0.23
     overall
    -0.23
     gameplay
    -0.22
     applicable
    -0.22
    æŃ¤æ¬¡
    -0.22
     scre
    -0.21
    人äºĭ
    -0.21
     cul
    -0.21
    STYPE
    -0.21
    partial
    -0.20
    POSITIVE LOGITS
    antly
    0.24
     freaking
    0.23
    纳米
    0.23
    ä¸įçIJĨ
    0.22
    ently
    0.22
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.21
     needless
    0.21
    _REQUIRE
    0.21
    pedia
    0.21
    å¾Ĺèµ·
    0.21
    Activations Density 0.372%

    No Known Activations