© 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. 12903
    Prev
    Next
    INDEX
    Explanations

    numeric and string key-value pairs

    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
    æĸĭ
    -0.06
    缮
    -0.06
    cken
    -0.06
     bê
    -0.06
    uns
    -0.06
    éģį
    -0.06
    pect
    -0.05
    /wp
    -0.05
     B
    -0.05
    [b
    -0.05
    POSITIVE LOGITS
    笳
    0.08
    azan
    0.08
     Purt
    0.08
    _ISS
    0.08
    _series
    0.08
    ensburg
    0.08
    ä¾¥
    0.08
    áŀģ
    0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.08
    ibaba
    0.08
    Activations Density 0.011%

    No Known Activations