© 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. 9176
    Prev
    Next
    INDEX
    Explanations

    explicit following words

    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
    zinho
    -0.09
    regor
    -0.07
    schaft
    -0.07
    вед
    -0.07
    æĺ¯ä¸įæĺ¯å¾Ī
    -0.07
    liness
    -0.07
    Ĺ
    -0.06
    hund
    -0.06
     effettivamente
    -0.06
    vole
    -0.06
    POSITIVE LOGITS
    ness
    0.13
    ely
    0.12
    -minded
    0.11
    ly
    0.11
    ively
    0.11
    amente
    0.10
    ation
    0.09
    idades
    0.09
    andex
    0.08
    æĻ°
    0.08
    Activations Density 0.013%

    No Known Activations