© 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. 47561
    Prev
    Next
    INDEX
    Explanations

    orthogonal projection

    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
    acer
    -0.07
    inato
    -0.07
    reon
    -0.06
    æĸŃæ¡¥
    -0.06
    ######
    -0.06
    åijĽ
    -0.06
    zal
    -0.06
    /tty
    -0.06
     saud
    -0.06
    å°ıæ¡¥
    -0.06
    POSITIVE LOGITS
    æĹĭ转
    0.10
    æĹĭ
    0.09
     rotations
    0.09
    rotation
    0.09
    Rotation
    0.09
    .har
    0.08
    vecs
    0.08
     Rot
    0.08
     rotation
    0.08
    éĺµ
    0.08
    Activations Density 0.002%

    No Known Activations