© 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. 15214
    Prev
    Next
    INDEX
    Explanations

    excluding, without, provided, minus

    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
    avid
    -0.09
    è¨İ
    -0.08
     ::=
    -0.08
    èº
    -0.07
    Configurer
    -0.07
    olk
    -0.07
    pedia
    -0.07
     lắm
    -0.07
    åĭ
    -0.07
    _finalize
    -0.07
    POSITIVE LOGITS
     hypothetical
    0.16
    è¯ķè¯ķçľĭ
    0.15
    è¯ķæİ¢
    0.14
    è¯ķ
    0.14
     hypoth
    0.14
    è¯ķä¸Ģè¯ķ
    0.13
     thá»Ń
    0.13
    è¯ķè¯ķ
    0.13
     test
    0.12
    è¯ķçĿĢ
    0.12
    Activations Density 0.207%

    No Known Activations