© 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. 15407
    Prev
    Next
    INDEX
    Explanations

    code declarations and imports

    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
    orar
    -0.08
     intele
    -0.08
    以ä¸Ĭå°±æĺ¯
    -0.07
    以ä¸ĬåĨħ容
    -0.07
    对ä¸Ĭè¿°
    -0.07
    ulier
    -0.07
    è£ħ饰设计
    -0.07
    åı¦å¤ĸä¸Ģ个
    -0.07
    ENTI
    -0.07
    _ok
    -0.07
    POSITIVE LOGITS
    Į¨
    0.07
    rung
    0.07
    å¼Ī
    0.06
    端åĢª
    0.06
    åħ³çħ§
    0.06
    äºīåĪĽ
    0.06
    ç®Ģ称
    0.06
    "They
    0.06
    duce
    0.06
    æľµ
    0.06
    Activations Density 0.058%

    No Known Activations