© 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. 19569
    Prev
    Next
    INDEX
    Explanations

    of or related to branches

    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
    -scalable
    -0.08
    æľ¬çīĪ
    -0.08
    eixe
    -0.08
     nejen
    -0.07
    takan
    -0.07
    BYTE
    -0.07
    ENTIC
    -0.07
    mato
    -0.07
    çİĩè¾¾
    -0.07
    /stretch
    -0.07
    POSITIVE LOGITS
     or
    0.08
    /
    0.07
    ãģĦãģŁãĤĬ
    0.06
    ãģłãģ£ãģŁãĤĬ
    0.06
    æĪĸèĢħ说
    0.06
    หรืà¸Ń
    0.06
    å°±ä¼ļ导èĩ´
    0.06
    vers
    0.06
    KO
    0.06
     etc
    0.06
    Activations Density 0.010%

    No Known Activations