© 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. 29526
    Prev
    Next
    INDEX
    Explanations

    method, output, date, services, editor

    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
    临
    -0.08
    basePath
    -0.08
    åĪ©
    -0.08
    çĻ¾è®¡
    -0.08
    åĵij
    -0.07
    à¹Ħà¸ĩ
    -0.07
    -FIRST
    -0.07
    ');"
    -0.07
    retta
    -0.07
    ä¹ħèĢĮ
    -0.07
    POSITIVE LOGITS
    ryn
    0.08
    æī¬
    0.08
    .alt
    0.07
     Kiel
    0.07
    che
    0.07
    uvan
    0.07
    æł¡åĽ¢å§Ķ
    0.07
    åĩºä¸Ģçīĩ
    0.07
    æ¬Ħ
    0.07
    æıļ
    0.07
    Activations Density 0.004%

    No Known Activations