© 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. 11223
    Prev
    Next
    INDEX
    Explanations

    case context

    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
    çĻ»å½ķæŁ¥çľĭ
    -0.07
    æĬľ
    -0.07
    -style
    -0.07
    轩
    -0.07
    åı¯æľī
    -0.06
    bürger
    -0.06
    enschaft
    -0.06
    ieÃŁ
    -0.06
    imed
    -0.06
    大åĪ©
    -0.06
    POSITIVE LOGITS
     location
    0.09
    uris
    0.08
    éĻĦè¿ij
    0.08
    éĻĦè¿ijçļĦ
    0.08
     locations
    0.08
    location
    0.08
     vicinity
    0.08
    ẩn
    0.08
     speedy
    0.07
    ä½įäºİ
    0.07
    Activations Density 0.005%

    No Known Activations