© 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. 48833
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas or hyphens

    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
    ifr
    -0.07
    orii
    -0.07
    æĬĺèħ¾
    -0.07
    jadi
    -0.07
    jis
    -0.07
    ä¹ĭ称
    -0.07
    {:
    -0.07
    æºľæºľ
    -0.06
    upload
    -0.06
    ungsk
    -0.06
    POSITIVE LOGITS
     Stich
    0.08
    æķı
    0.07
    çī©
    0.07
    anen
    0.07
    utki
    0.07
    éĿĸ
    0.07
     Blasio
    0.06
    elps
    0.06
     change
    0.06
    REST
    0.06
    Activations Density 0.008%

    No Known Activations