© 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. 45574
    Prev
    Next
    INDEX
    Explanations

    html/xml structural elements

    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
    ements
    -0.07
    datap
    -0.07
    sert
    -0.07
    ohan
    -0.07
    '):
    -0.06
    à·ĥ
    -0.06
    ahlung
    -0.06
    éĽª
    -0.06
    orti
    -0.06
    eled
    -0.06
    POSITIVE LOGITS
    isst
    0.08
    á»įa
    0.07
    }
    0.07
    веÑĢи
    0.07
    IntegerField
    0.07
    çĥŃéŨæIJľç´¢
    0.07
     ldb
    0.06
     mes
    0.06
    ารà¸ĸ
    0.06
     ex
    0.06
    Activations Density 0.128%

    No Known Activations