© 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. 2095
    Prev
    Next
    INDEX
    Explanations

    true or false

    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
    .mm
    -0.08
     yyyy
    -0.07
    pery
    -0.07
    飶åįİ
    -0.07
    itemap
    -0.07
    NotAllowed
    -0.07
    utang
    -0.07
    Pacific
    -0.07
    ä½ĵçİ°åľ¨
    -0.07
    æį¢æĪIJ
    -0.07
    POSITIVE LOGITS
    ugu
    0.08
    OBO
    0.07
    ugo
    0.07
    媳
    0.07
    ENSOR
    0.07
    ¹
    0.06
    inke
    0.06
    oji
    0.06
    忽
    0.06
    éĢłçī©
    0.06
    Activations Density 0.015%

    No Known Activations