© 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. 31991
    Prev
    Next
    INDEX
    Explanations

    change, transformation, or process

    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
    å¾ĹæĦı
    -0.08
    _periods
    -0.08
    úm
    -0.08
    åħ±äº«
    -0.08
    omos
    -0.07
    oppable
    -0.07
    Selectable
    -0.07
    ngua
    -0.07
    ç¯Ļ
    -0.07
    çļĦé«ĺæīĭ
    -0.07
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭ
    0.07
    ock
    0.07
    vation
    0.07
    è¿ĩç¨ĭ
    0.07
    isman
    0.07
    arness
    0.07
    pecific
    0.07
    çĦ
    0.07
    è¿ĩç¨ĭçļĦ
    0.07
    ivanje
    0.07
    Activations Density 0.008%

    No Known Activations