© 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. 10580
    Prev
    Next
    INDEX
    Explanations

    translation, shifting, offset

    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
     ratios
    -0.08
    ambo
    -0.08
    ium
    -0.08
    æ¯Ķçİĩ
    -0.08
    ordio
    -0.08
    åѦä¸ļ
    -0.08
    丹éĿĴ
    -0.08
     Rates
    -0.07
    oyer
    -0.07
    ratio
    -0.07
    POSITIVE LOGITS
    åģı移
    0.13
     offset
    0.12
     shift
    0.12
    平移
    0.12
    (offset
    0.12
     shifting
    0.11
    offset
    0.11
    移ä½į
    0.11
    .shift
    0.11
    shift
    0.11
    Activations Density 0.020%

    No Known Activations