© 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. 34032
    Prev
    Next
    INDEX
    Explanations

    indices of higher order

    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
    en
    -0.16
    ly
    -0.15
    Ùĩ
    -0.13
    an
    -0.12
    zelfde
    -0.12
    n
    -0.12
    u
    -0.11
    ed
    -0.11
    ers
    -0.11
    b
    -0.11
    POSITIVE LOGITS
    <|box_end|>
    0.13
    enticated
    0.11
    annya
    0.10
    eldes
    0.10
    tures
    0.10
    Ù°
    0.10
    arness
    0.09
    ë¦Ħ
    0.09
    ascript
    0.09
    arning
    0.09
    Activations Density 0.043%

    No Known Activations