© 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. 22024
    Prev
    Next
    INDEX
    Explanations

    \limits _{

    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
    erg
    -0.10
    ritz
    -0.08
    ited
    -0.08
    ra
    -0.08
    h
    -0.08
    ang
    -0.07
    ot
    -0.07
    rit
    -0.07
    c
    -0.07
    ic
    -0.07
    POSITIVE LOGITS
    enteil
    0.08
    elum
    0.08
    estes
    0.08
    å°Ķé¡¿
    0.07
    secs
    0.07
    cesi
    0.07
    istes
    0.07
    onan
    0.07
    fahrens
    0.07
    檻
    0.07
    Activations Density 0.002%

    No Known Activations