© 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. 25612
    Prev
    Next
    INDEX
    Explanations

    number or word

    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
    ile
    -0.08
    igli
    -0.08
     Soll
    -0.07
    iles
    -0.07
    führ
    -0.06
    edale
    -0.06
    ÙĪÙĦÙĬÙĪ
    -0.06
    _RAD
    -0.06
    /rand
    -0.06
    affle
    -0.06
    POSITIVE LOGITS
    legate
    0.08
    ستÙĨ
    0.07
    elter
    0.07
    oder
    0.07
    éªĨ
    0.07
    elo
    0.07
    æ¯ĵ
    0.07
    ÌĢ
    0.07
    åľ°åľ¨
    0.07
    缸æī£
    0.07
    Activations Density 0.069%

    No Known Activations