© 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. 49696
    Prev
    Next
    INDEX
    Explanations

    linear relationships

    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
    инÑģÑĤва
    -0.08
    æݪ置
    -0.08
    uide
    -0.08
    åIJĮåIJį
    -0.08
    _unused
    -0.08
     ròng
    -0.08
     unthinkable
    -0.08
    angsa
    -0.08
     reper
    -0.07
    egrity
    -0.07
    POSITIVE LOGITS
    æĭŁåIJĪ
    0.13
     shape
    0.10
     fit
    0.10
     nonlinear
    0.10
     fitted
    0.10
    线æĢ§
    0.09
    éĿŀ线æĢ§
    0.09
    shape
    0.09
    -linear
    0.09
     linear
    0.09
    Activations Density 0.043%

    No Known Activations