© 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. 3142
    Prev
    Next
    INDEX
    Explanations

    `.target`, `.currentTarget`, `stdin`

    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
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.08
    OBO
    -0.07
    коÑģ
    -0.07
    alak
    -0.07
    积累äºĨ丰å¯ĮçļĦ
    -0.07
    ODO
    -0.07
    aldo
    -0.07
    _unpack
    -0.06
    lix
    -0.06
    æĿ¥å¾Ģ
    -0.06
    POSITIVE LOGITS
    ÙĬاÙĨ
    0.08
    奴
    0.07
    欲
    0.07
    çģµ
    0.06
    è¥Ħ
    0.06
    inov
    0.06
    bruck
    0.06
    åĴĮæĪijçļĦ
    0.06
     humid
    0.06
    pjes
    0.06
    Activations Density 0.001%

    No Known Activations