© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20298
    Prev
    Next
    INDEX
    Explanations

    vim settings or special tokens

    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
    o
    -0.16
    an
    -0.15
    Ùĩ
    -0.14
    d
    -0.14
    m
    -0.13
    i
    -0.13
    en
    -0.12
    c
    -0.12
    es
    -0.12
    n
    -0.12
    POSITIVE LOGITS
    <|box_end|>
    0.17
    gether
    0.13
    odore
    0.13
    htable
    0.13
    enticate
    0.12
    翼翼
    0.12
    obiet
    0.12
    aminer
    0.12
    onsor
    0.11
    bidden
    0.11
    Activations Density 0.726%

    No Known Activations