© 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. 3927
    Prev
    Next
    INDEX
    Explanations

    shift or timing changes

    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
    å¤©åľ°éĹ´
    -0.08
    ogli
    -0.07
     Stateless
    -0.07
    çīį
    -0.07
     stup
    -0.07
    æĥħæĦı
    -0.07
    çĶŁæ°´
    -0.07
    רק
    -0.06
    INAN
    -0.06
     perd
    -0.06
    POSITIVE LOGITS
    shift
    0.12
     shift
    0.12
     shifts
    0.11
    hift
    0.11
    .shift
    0.11
    åģı移
    0.11
    Shift
    0.10
     shifting
    0.10
     Shift
    0.10
    -shift
    0.10
    Activations Density 0.079%

    No Known Activations