© 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. 60381
    Prev
    Next
    INDEX
    Explanations

    transform

    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
    æī¼
    -0.08
    顺æīĭ
    -0.07
    éĵł
    -0.07
     избÑĢан
    -0.07
    éĢīçĶ¨
    -0.07
    LEC
    -0.07
    è·Łèĩªå·±
    -0.06
    ocado
    -0.06
    åĬ¨æijĩ
    -0.06
    以åħį
    -0.06
    POSITIVE LOGITS
     Transform
    0.09
    .transform
    0.09
     transform
    0.09
     transformation
    0.09
    transform
    0.08
    Transform
    0.08
    转æį¢
    0.08
    _transform
    0.08
     transforma
    0.08
    媳
    0.08
    Activations Density 0.077%

    No Known Activations