© 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. 56441
    Prev
    Next
    INDEX
    Explanations

    reverse, orientation, direction, shift

    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
    _splits
    -0.08
    èĨĬ
    -0.08
    miss
    -0.08
    éĽ¯
    -0.08
    .Resolve
    -0.08
    çŁ
    -0.08
     bén
    -0.07
    anita
    -0.07
    pty
    -0.07
    鼨
    -0.07
    POSITIVE LOGITS
     reverse
    0.10
     reversed
    0.10
    åıįåIJij
    0.09
     Retro
    0.09
    egative
    0.09
    reverse
    0.09
    éĢĨåIJij
    0.09
     retro
    0.09
    éĢĨæµģ
    0.08
    éĢĨ转
    0.08
    Activations Density 0.010%

    No Known Activations