© 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. 18228
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åºŁè¯Ŀ
    -0.08
     minimum
    -0.07
    Ratio
    -0.06
     Type
    -0.06
    ensus
    -0.06
     Total
    -0.06
    _extra
    -0.06
     total
    -0.06
     ratio
    -0.06
    ÏĨο
    -0.06
    POSITIVE LOGITS
    éłĨçķª
    0.09
    .rot
    0.08
     orthogonal
    0.08
     кÑĢово
    0.08
    rotate
    0.08
    ROT
    0.08
    çŁ¢éĩı
    0.08
    åī
    0.08
    avier
    0.08
     rotations
    0.08
    Activations Density 0.000%

    No Known Activations