© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62781
    Prev
    Next
    INDEX
    Explanations

    code patterns

    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
    åİŁåĪĻä¸Ĭ
    -0.07
    .SK
    -0.07
     Palme
    -0.07
    mute
    -0.07
     optim
    -0.06
     gamm
    -0.06
    OME
    -0.06
     Herm
    -0.06
    ä¸Ģåı¥
    -0.06
    大åIJį
    -0.06
    POSITIVE LOGITS
    æĪij们çľĭåĪ°
    0.10
    æĽ´åĥıæĺ¯
    0.09
    reon
    0.08
    keh
    0.07
    uster
    0.07
    à¹īม
    0.07
    ëįĶëĭĪ
    0.07
    ystick
    0.07
     evident
    0.07
    sembl
    0.07
    Activations Density 0.060%

    No Known Activations