© 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. 19401
    Prev
    Next
    INDEX
    Explanations

    code block structure, function definitions

    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
     Rel
    -0.06
     rel
    -0.06
    çī¹å°Ķ
    -0.06
    ao
    -0.06
     x
    -0.06
    ouse
    -0.06
     s
    -0.06
    大æ´ĭ
    -0.05
    缮çļĦæĺ¯
    -0.05
    dj
    -0.05
    POSITIVE LOGITS
    )((((
    0.08
    omag
    0.08
    åijĽ
    0.07
    strup
    0.07
    rotch
    0.07
    laat
    0.07
    amour
    0.07
    åīį款
    0.07
    åİĨæŶ
    0.07
    InMillis
    0.07
    Activations Density 0.006%

    No Known Activations