© 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. 27712
    Prev
    Next
    INDEX
    Explanations

    target

    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
    ê¹IJ
    -0.11
    ately
    -0.08
    aring
    -0.08
    idable
    -0.08
    ¹
    -0.07
    ointed
    -0.07
    ette
    -0.06
     tạp
    -0.06
    ilde
    -0.06
    aid
    -0.06
    POSITIVE LOGITS
    ted
    0.12
    ting
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.10
    jent
    0.10
    /target
    0.09
    assem
    0.09
    esseract
    0.09
    à¸ģารà¸ĵà¹Į
    0.09
    erait
    0.09
    sWith
    0.09
    Activations Density 0.031%

    No Known Activations