© 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. 46932
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    ness
    -0.19
    tures
    -0.16
    ificates
    -0.14
    onical
    -0.13
    apsed
    -0.13
    istration
    -0.13
    hood
    -0.13
    并èĮĤ
    -0.12
    oenix
    -0.12
    tedir
    -0.12
    POSITIVE LOGITS
    Ùĩ
    0.34
    en
    0.25
    ãĥ³
    0.24
    es
    0.21
    u
    0.20
    an
    0.19
    er
    0.19
    ed
    0.17
    i
    0.16
    as
    0.15
    Activations Density 4.289%

    No Known Activations