© 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. 12161
    Prev
    Next
    INDEX
    Explanations

    authenticated, -ized

    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
    vod
    -0.09
    holz
    -0.07
     Tonight
    -0.07
    umm
    -0.07
    导åĩº
    -0.07
    žel
    -0.07
    lande
    -0.07
    _frames
    -0.07
    åıĹè¿ĩ
    -0.07
    вÑĢи
    -0.07
    POSITIVE LOGITS
    ä»ĺãģį
    0.07
    ated
    0.07
    çīĪ
    0.07
    äºĨçļĦ
    0.07
    anced
    0.07
    -enabled
    0.07
    åĬłæĭī
    0.06
    ized
    0.06
    oge
    0.06
    Ỽ
    0.06
    Activations Density 0.380%

    No Known Activations