© 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. 27480
    Prev
    Next
    INDEX
    Explanations

    Let $

    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
    umpt
    -0.08
    cats
    -0.07
    VED
    -0.06
    è¿Ļä¸ĢåĪ»
    -0.06
    sy
    -0.06
    thal
    -0.06
    amura
    -0.06
    第ä¸Ģçľ¼
    -0.06
    _LEG
    -0.06
    case
    -0.06
    POSITIVE LOGITS
    å§ĭèĩ³
    0.09
    åĮĹé£İ
    0.07
    ШÐIJ
    0.07
    halen
    0.07
    .opens
    0.07
    orem
    0.07
    以ä¸ĭæĿ¡ä»¶
    0.07
    áĢĶáĢºáĢ¸
    0.07
    éĥ½æĺ¯ä¸Ģ个
    0.07
    ãģ¯ãģĦãģĭãģĮ
    0.06
    Activations Density 0.068%

    No Known Activations