© 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. 43592
    Prev
    Next
    INDEX
    Explanations

    for context

    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
    jenigen
    -0.07
    hold
    -0.07
    assi
    -0.07
    ator
    -0.07
    _ASM
    -0.07
    cati
    -0.07
    zit
    -0.06
    asi
    -0.06
    ey
    -0.06
    entina
    -0.06
    POSITIVE LOGITS
    ç´ł
    0.07
    è¾Ħ
    0.07
    okon
    0.07
    ikkan
    0.07
    .Entry
    0.07
    稣
    0.07
    çī¹å®ļ
    0.06
    ipher
    0.06
    ä¸Ģéģį
    0.06
    IZA
    0.06
    Activations Density 0.031%

    No Known Activations