© 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. 38939
    Prev
    Next
    INDEX
    Explanations

    certain predictors

    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
     thus
    -0.07
    ÑĩиÑĤа
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    Ñħан
    -0.07
    idon
    -0.07
    Äģja
    -0.07
     sometimes
    -0.07
    ãģĵãĤĮãģ¯
    -0.07
    klin
    -0.07
    indr
    -0.07
    POSITIVE LOGITS
    بات
    0.07
    prompt
    0.07
    engan
    0.07
    hum
    0.06
    ares
    0.06
    emis
    0.06
    æĢĢæŁĶ
    0.06
     Firstly
    0.06
     relevant
    0.06
    tti
    0.06
    Activations Density 0.031%

    No Known Activations