© 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. 64470
    Prev
    Next
    INDEX
    Explanations

    code identifiers like name, id, or function

    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
    è¿ŀäºij
    -0.10
    á»ijn
    -0.08
    ÙĬاÙĨ
    -0.07
    edur
    -0.07
    uos
    -0.07
    æĤ´
    -0.07
    ndl
    -0.07
    ovit
    -0.07
    iette
    -0.07
    çļĦå¿ĥèĦı
    -0.07
    POSITIVE LOGITS
    好åIJİ
    0.09
    å¾Ĺå¾Ī
    0.07
    å®ĮåIJİ
    0.07
    nya
    0.07
    anch
    0.07
    rech
    0.06
    åĭĩå¾Ģ缴åīį
    0.06
    å¾ĹæĽ´
    0.06
    encies
    0.06
    ÑĮ
    0.06
    Activations Density 0.035%

    No Known Activations