© 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. 29308
    Prev
    Next
    INDEX
    Explanations

    pine

    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
    ä¼¼
    -0.09
    ỡ
    -0.08
    acked
    -0.08
    urch
    -0.08
     licha
    -0.07
    /documents
    -0.07
    eshire
    -0.07
    ¿
    -0.07
    деÑģÑı
    -0.07
    roud
    -0.07
    POSITIVE LOGITS
    éĹĨ
    0.07
    éĺħ读åİŁæĸĩ
    0.07
    çıĬçıĬ
    0.07
    esson
    0.07
    ç¾Ĭç¾Ĭ
    0.07
    æ¦Ľ
    0.06
    .OR
    0.06
     thereby
    0.06
    Pts
    0.06
    绯
    0.06
    Activations Density 0.002%

    No Known Activations