© 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. 56982
    Prev
    Next
    INDEX
    Explanations

    lines of code

    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
    дÑĢÑĥ
    -0.07
    边走
    -0.07
     Vig
    -0.06
    åħĪä»İ
    -0.06
    é£İåIJ¹
    -0.06
    Har
    -0.06
    ipt
    -0.06
    åľ¨åIJĦ
    -0.06
    ober
    -0.06
    strup
    -0.05
    POSITIVE LOGITS
    åĭĭ
    0.08
    æīĵäºĨ
    0.08
    lock
    0.07
    erosis
    0.07
     rap
    0.07
    eros
    0.07
    .Transport
    0.07
    请ä¸ĭè½½
    0.07
     pouv
    0.07
    rap
    0.07
    Activations Density 0.001%

    No Known Activations