© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49902
    Prev
    Next
    INDEX
    Explanations

    namespaced programming constructs

    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
    enburg
    -0.08
    ,[],
    -0.07
    éħĿ
    -0.07
    亲身ä½ĵ
    -0.07
    [hash
    -0.07
    /cop
    -0.07
    ][]
    -0.07
     tslint
    -0.07
    atham
    -0.07
    åĩºæĸ°
    -0.06
    POSITIVE LOGITS
    å°ĸ
    0.07
    omit
    0.06
    _clause
    0.06
    lit
    0.06
    宣
    0.06
     Trailer
    0.06
     Chauff
    0.06
    noc
    0.06
     afar
    0.06
    ç¾İäºĨ
    0.06
    Activations Density 0.905%

    No Known Activations