© 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. 21969
    Prev
    Next
    INDEX
    Explanations

    Henna pattern

    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
    izr
    -0.07
    رائ
    -0.07
    (dl
    -0.07
    رØŃ
    -0.07
    oller
    -0.07
    ừa
    -0.07
     itemprop
    -0.07
    ilit
    -0.07
    <d
    -0.07
    åĪĿå§ĭåĮĸ
    -0.07
    POSITIVE LOGITS
    ocas
    0.08
    appa
    0.07
    _province
    0.07
    ogn
    0.07
    åºĶçĶ¨åĪ°
    0.06
    å¥ĩ
    0.06
    ç«ŀäºīé£İéĻ©
    0.06
    å¥ĩçļĦ
    0.06
    湿çĸ£
    0.06
    åħ¨ä¸ĸçķĮçļĦ
    0.06
    Activations Density 0.022%

    No Known Activations