© 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. 2488
    Prev
    Next
    INDEX
    Explanations

    about

    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
    Again
    -0.26
    ç»ıéªĮåĢ¼
    -0.25
    _SCR
    -0.23
    Presence
    -0.23
    edReader
    -0.23
    ypse
    -0.22
     only
    -0.22
    ä¸Ģ段æŶéĹ´
    -0.22
    æīĢæľī人éĥ½
    -0.22
    presence
    -0.22
    POSITIVE LOGITS
    è¿Ļåľº
    0.26
    æѤäºĭ
    0.26
    è¿Ļ项
    0.26
     topics
    0.25
    è¿Ļä½į
    0.24
    è¿Ļ个éĹ®é¢ĺ
    0.23
     Interesting
    0.23
     elig
    0.23
    è¿ĻæĿ¡è·¯
    0.23
    ä»Ģä¹Īæĺ¯
    0.23
    Activations Density 0.039%

    No Known Activations