© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    grid and breaks

    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
    ÏĥÏĥ
    -0.09
    bacher
    -0.07
    ukat
    -0.07
    ÐijÐł
    -0.07
    åIJĪ家
    -0.06
    atico
    -0.06
     remise
    -0.06
     Quellen
    -0.06
    ese
    -0.06
    baka
    -0.06
    POSITIVE LOGITS
     grid
    0.11
    ç½ijæł¼
    0.11
     discret
    0.11
     Grid
    0.10
    Grid
    0.10
    grid
    0.10
     interpolated
    0.09
    åĪĨ辨çİĩ
    0.09
     finer
    0.09
    å¯Ĩå¸ĥ
    0.09
    Activations Density 0.069%

    No Known Activations