© 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. 27826
    Prev
    Next
    INDEX
    Explanations

    SD or state followed by various punctuation

    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
    erner
    -0.08
    å¤Ħå¤Ħ
    -0.07
    âĺħâĺĨ
    -0.07
    _SYN
    -0.07
    اÙģ
    -0.07
    orns
    -0.07
    ìĿ´íģ¬
    -0.07
    iele
    -0.07
    ä¸įåı¯æĢķ
    -0.07
    ØŃÙĬ
    -0.07
    POSITIVE LOGITS
    -dropdown
    0.08
    ä¸įæŃ»
    0.07
    asio
    0.07
    ä¸įæīĵ
    0.07
    бби
    0.06
    _factory
    0.06
    à¹Ģหà¸Ļ
    0.06
    oteca
    0.06
    åĿ
    0.06
    åıªèĥ½æĺ¯
    0.06
    Activations Density 0.001%

    No Known Activations