© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13425
    Prev
    Next
    INDEX
    Explanations

    output, exit, induction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arang
    -0.07
    èĩ
    -0.07
    æ¼ł
    -0.06
    rowned
    -0.06
    .solve
    -0.06
    åħ³èģĶæĢ§
    -0.06
    以身
    -0.06
     boundaries
    -0.06
     unfamiliar
    -0.06
    Ïĥκ
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.11
     feed
    0.10
    缴æİ¥è¿Ľåħ¥
    0.10
    è¿ĻèĤ¡
    0.10
     feeding
    0.10
    ç»ıè¿ĩ
    0.10
     feeds
    0.09
    ç¶ĵéģİ
    0.09
    éľĢè¦ģç»ıè¿ĩ
    0.09
    wege
    0.09
    Activations Density 0.285%

    No Known Activations