© 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. 65508
    Prev
    Next
    INDEX
    Explanations

    hexadecimal codes and identifiers

    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
    e
    -0.12
    a
    -0.11
    d
    -0.09
    s
    -0.09
    c
    -0.09
    n
    -0.08
    sa
    -0.08
    Ùĭ
    -0.08
    f
    -0.08
    v
    -0.08
    POSITIVE LOGITS
    лип
    0.10
    ллин
    0.10
    empa
    0.10
    agak
    0.10
    abbo
    0.09
    imbus
    0.08
    akat
    0.08
    è¯ł
    0.08
    Allem
    0.08
    urusan
    0.08
    Activations Density 0.068%

    No Known Activations