© 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. 60713
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    ogra
    -0.07
    رÙĤ
    -0.06
     D
    -0.06
     Alias
    -0.06
    رائ
    -0.06
     d
    -0.06
    orte
    -0.06
    /modules
    -0.06
    é²ľ
    -0.06
    ober
    -0.06
    POSITIVE LOGITS
    è²
    0.08
    asten
    0.07
    ointed
    0.07
    ìĿ´ë²Ħ
    0.07
     apre
    0.07
    omie
    0.07
    iose
    0.07
    TriState
    0.07
    _HT
    0.07
    对ä¸Ĭè¿°
    0.07
    Activations Density 0.002%

    No Known Activations