© 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. 63795
    Prev
    Next
    INDEX
    Explanations

    energy, Frame, costs, offsets, Model

    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
    cind
    -0.08
    étrica
    -0.07
    phant
    -0.07
    aille
    -0.07
     kell
    -0.07
    ä¼łè¯´ä¸ŃçļĦ
    -0.07
    缸éļĶ
    -0.07
    esser
    -0.07
    gnore
    -0.07
    .leave
    -0.07
    POSITIVE LOGITS
    大æľī
    0.07
    åĴĮ交æµģ
    0.06
    å¤
    0.06
    éļı
    0.06
    ä¼ļéļıçĿĢ
    0.06
    healthy
    0.06
    rng
    0.06
    éļ¨
    0.06
    çłģ
    0.06
    ä¸İ交æµģ
    0.06
    Activations Density 0.074%

    No Known Activations