© 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. 39583
    Prev
    Next
    INDEX
    Explanations

    manifold

    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
    æŀĿ
    -0.08
     fix
    -0.07
     call
    -0.07
    ç²Ĵ度
    -0.07
    ç¿İ
    -0.06
     Nest
    -0.06
    åĽºå®ļåľ¨
    -0.06
    åĽºå®ļ
    -0.06
    ä¸ĢæŀĿ
    -0.06
     fixed
    -0.06
    POSITIVE LOGITS
    ëį§
    0.08
     uÄŁ
    0.08
    大æ±ī
    0.08
     enclosing
    0.08
    ecture
    0.07
     twists
    0.07
    inci
    0.07
    CONFIG
    0.07
    clas
    0.07
     Hamil
    0.07
    Activations Density 0.010%

    No Known Activations