© 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. 32562
    Prev
    Next
    INDEX
    Explanations

    entication, enticate, aghers

    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
    en
    -0.21
    Ùĩ
    -0.20
    es
    -0.18
    o
    -0.18
    an
    -0.18
    al
    -0.18
    er
    -0.17
    u
    -0.16
    h
    -0.15
    in
    -0.14
    POSITIVE LOGITS
    翼翼
    0.15
    agher
    0.13
    entication
    0.13
    并èĮĤ
    0.12
    ìį¨
    0.12
    ewise
    0.11
    ussion
    0.10
    enticate
    0.10
    ä¸įç´Ĭ
    0.10
    jenigen
    0.10
    Activations Density 1.375%

    No Known Activations