© 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. 25360
    Prev
    Next
    INDEX
    Explanations

    linear combinations of functions

    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
    annotate
    -0.07
    PLIC
    -0.06
    udi
    -0.06
    ÄįÃŃ
    -0.06
    åĽĽçĤ¹
    -0.06
    ijľ
    -0.06
    adrat
    -0.06
    æĽ´åIJį
    -0.06
    زر
    -0.06
    ivr
    -0.06
    POSITIVE LOGITS
    projection
    0.08
     decomposition
    0.08
    _locals
    0.08
    .fft
    0.08
     projections
    0.08
    ä¸Ģç½ij
    0.08
     projection
    0.08
    egov
    0.07
    éĢĨåıĺ
    0.07
     Fourier
    0.07
    Activations Density 0.015%

    No Known Activations