© 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. 33394
    Prev
    Next
    INDEX
    Explanations

    code structure syntax

    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
    egin
    -0.07
    ilde
    -0.07
    çĶ¸
    -0.07
     ÙħÙħ
    -0.07
    allon
    -0.07
    erto
    -0.06
    alter
    -0.06
    ere
    -0.06
    icar
    -0.06
    [section
    -0.06
    POSITIVE LOGITS
    è¡·
    0.08
    aed
    0.08
     surpr
    0.07
    óm
    0.07
    leta
    0.07
    æĸ°ç¤¾
    0.07
    úd
    0.07
     occupation
    0.06
    unas
    0.06
    evos
    0.06
    Activations Density 0.004%

    No Known Activations