© 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. 61079
    Prev
    Next
    INDEX
    Explanations

    eagger

    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
    lett
    -0.08
    asar
    -0.08
    boo
    -0.08
    URED
    -0.08
    stral
    -0.08
    ish
    -0.08
    beit
    -0.08
     поводÑĥ
    -0.07
    ificio
    -0.07
    بطاÙĦ
    -0.07
    POSITIVE LOGITS
    oriously
    0.09
    ammers
    0.07
    ï¸İ
    0.07
    rees
    0.07
    agger
    0.07
    olica
    0.06
     ger
    0.06
     Lainnya
    0.06
    æĽ¦
    0.06
    inition
    0.06
    Activations Density 0.001%

    No Known Activations