© 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. 19583
    Prev
    Next
    INDEX
    Explanations

    sentence end followed by common words

    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
    ly
    -0.07
     Kel
    -0.07
    °
    -0.06
    elter
    -0.06
     \`
    -0.06
    θή
    -0.06
    Bindings
    -0.06
    _bindings
    -0.06
    andi
    -0.06
    aglia
    -0.06
    POSITIVE LOGITS
    жÑĥ
    0.07
    æľĢè¿ijæĽ´æĸ°
    0.07
    ourn
    0.07
    äºĤ
    0.07
    towe
    0.07
    anness
    0.07
    udge
    0.07
    alama
    0.07
    नà¥į
    0.07
    rast
    0.07
    Activations Density 0.027%

    No Known Activations