© 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. 12841
    Prev
    Next
    INDEX
    Explanations

    between regions or spaces

    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
    .endpoint
    -0.08
    á»ĭch
    -0.08
     hany
    -0.07
    åįĬå¤ľ
    -0.07
    ugno
    -0.07
    anh
    -0.07
    abr
    -0.07
    è¸ıè¸ıå®ŀ
    -0.07
    listing
    -0.07
    ç§ij夫
    -0.07
    POSITIVE LOGITS
     between
    0.16
     междÑĥ
    0.15
     Between
    0.15
    -between
    0.15
    Between
    0.14
     بÙĬÙĨÙĩا
    0.14
    between
    0.14
     BETWEEN
    0.14
    _between
    0.14
     zwischen
    0.13
    Activations Density 0.141%

    No Known Activations