© 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. 10922
    Prev
    Next
    INDEX
    Explanations

    expect "missing" or "prints"

    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
    odoro
    -0.08
    Įĵ
    -0.08
    ¬ģ
    -0.07
    ogo
    -0.07
    ium
    -0.07
    è¿Ļ个åĵģçīĮ
    -0.07
    对äºİä¸ĢäºĽ
    -0.07
    ÏĦοÏĢοι
    -0.07
    िस
    -0.07
    asher
    -0.07
    POSITIVE LOGITS
     noqa
    0.07
    dar
    0.07
    =:
    0.07
    eer
    0.07
    uk
    0.07
    ä¸Ģä½ľ
    0.06
    ñas
    0.06
    使çĶ¨åĴĮ
    0.06
    ç»°
    0.06
    ž
    0.06
    Activations Density 0.003%

    No Known Activations