© 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. 2135
    Prev
    Next
    INDEX
    Explanations

    t-tests statistical analysis

    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
    ctal
    -0.08
     ngạch
    -0.08
    enef
    -0.07
    asher
    -0.07
    generation
    -0.07
    ëijĺ
    -0.07
    cce
    -0.07
    tecz
    -0.06
    .removeClass
    -0.06
     Evel
    -0.06
    POSITIVE LOGITS
    æľªçŁ¥
    0.07
    aho
    0.07
    æľīéĻIJ
    0.07
     adi
    0.07
    æľŁéĻIJ为
    0.07
    æŁ´
    0.07
     Navarro
    0.07
    çħ§é¡¾
    0.07
    Unknown
    0.06
     counselling
    0.06
    Activations Density 0.002%

    No Known Activations