© 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. 45587
    Prev
    Next
    INDEX
    Explanations

    ascension, real numbers, Reverend

    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
    eting
    -0.08
    cock
    -0.07
    sworth
    -0.07
    rous
    -0.07
    sert
    -0.07
    gle
    -0.07
    é¡¿äºĨ
    -0.07
    çĪº
    -0.07
    etur
    -0.07
    astic
    -0.07
    POSITIVE LOGITS
    èµ
    0.07
    okit
    0.07
    置顶
    0.07
    ervations
    0.06
    urier
    0.06
    ovable
    0.06
     chau
    0.06
    èĺĭ
    0.06
    decess
    0.06
    èµĦ产éħįç½®
    0.06
    Activations Density 0.002%

    No Known Activations