© 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. 63669
    Prev
    Next
    INDEX
    Explanations

    special characters and keywords

    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
    ами
    -0.12
    <|box_end|>
    -0.11
    hood
    -0.10
    inson
    -0.09
    à±ģ
    -0.09
    ozo
    -0.09
    OwnProperty
    -0.09
    а
    -0.09
    oz
    -0.09
    ação
    -0.09
    POSITIVE LOGITS
    IENT
    0.08
    ëĿ½
    0.08
    ±
    0.08
    (
    0.07
    Ń
    0.07
    ãĥ³
    0.07
    ways
    0.07
    à¸ĩาà¸Ļ
    0.07
    à¸ģาร
    0.07
    icale
    0.06
    Activations Density 0.002%

    No Known Activations