© 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. 25261
    Prev
    Next
    INDEX
    Explanations

    approximately, rather, estimates

    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
    æ²ĥæĸ¯
    -0.08
    noinspection
    -0.08
    enix
    -0.07
    andia
    -0.07
    usic
    -0.07
    å®īå®ī
    -0.07
    inov
    -0.07
    缴æݥ被
    -0.07
    缴æİ¥ä¸İ
    -0.07
    ä¸į容
    -0.07
    POSITIVE LOGITS
     rather
    0.15
    èĢĮéĿŀ
    0.14
    èĢĮä¸įæĺ¯
    0.14
    rather
    0.14
     Rather
    0.12
    Rather
    0.10
     plutôt
    0.10
    èĢĮå·²
    0.10
     instead
    0.10
     chứ
    0.10
    Activations Density 0.116%

    No Known Activations