© 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. 42234
    Prev
    Next
    INDEX
    Explanations

    location in front of

    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
    γκ
    -0.07
    çĻ¾è®¡
    -0.07
     links
    -0.07
    Ùĥب
    -0.07
    okr
    -0.07
    峨çľī
    -0.07
    ØŃÙĬÙĨ
    -0.07
     Mol
    -0.07
    åĿIJåĪ°
    -0.06
    åij¨è¾¹çݯå¢ĥ
    -0.06
    POSITIVE LOGITS
    è¿Ļç§į人
    0.07
    ãģĹãģĭ
    0.07
     $__
    0.07
    -facing
    0.07
    راÙĤ
    0.07
    orat
    0.07
    -side
    0.07
    obe
    0.07
    chaft
    0.07
     parado
    0.06
    Activations Density 0.001%

    No Known Activations