© 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. 18229
    Prev
    Next
    INDEX
    Explanations

    card reader

    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
    anco
    -0.08
    оÑĢг
    -0.07
    ektor
    -0.07
    egn
    -0.07
    erte
    -0.07
    azard
    -0.06
    itarian
    -0.06
    venuto
    -0.06
    epad
    -0.06
    amburger
    -0.06
    POSITIVE LOGITS
    inality
    0.12
    apult
    0.09
    nection
    0.09
    reuse
    0.09
    reira
    0.09
    alog
    0.09
    ursive
    0.09
    valho
    0.09
    aceous
    0.08
    olina
    0.08
    Activations Density 0.061%

    No Known Activations