© 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. 2835
    Prev
    Next
    INDEX
    Explanations

    password, explain, hashCode

    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
    ä¼
    -0.07
    LOC
    -0.07
    嫦
    -0.07
    gages
    -0.06
    êu
    -0.06
    oco
    -0.06
    æݪ
    -0.06
    èĦijè¢ĭ
    -0.06
    æľĿå¤ķ
    -0.06
    身å¤Ħ
    -0.06
    POSITIVE LOGITS
    stad
    0.07
    ÑģÑĤил
    0.07
    ptest
    0.07
    asons
    0.07
    èľĤå·¢
    0.07
    趾
    0.07
    imson
    0.07
    äºĮçŃī
    0.07
     hasilnya
    0.06
     عزÙĬز
    0.06
    Activations Density 0.001%

    No Known Activations