© 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. 41751
    Prev
    Next
    INDEX
    Explanations

    US, housing, occurrence, chamber, motor

    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
    zwi
    -0.08
    lest
    -0.07
    éĨīäºĨ
    -0.07
     Coro
    -0.07
    казÑĭ
    -0.07
    ç¾²
    -0.07
    itra
    -0.07
    WithContext
    -0.07
    ÙģÛĮ
    -0.07
    +"]
    -0.07
    POSITIVE LOGITS
    踵
    0.06
    åı¯è§Ĩ
    0.06
    ä¸įæĪIJ
    0.06
    ZR
    0.06
    oplast
    0.06
    å¾ĹäºĨ
    0.06
    ender
    0.06
    åº
    0.06
    é¢ł
    0.05
    annon
    0.05
    Activations Density 0.201%

    No Known Activations