© 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. 15228
    Prev
    Next
    INDEX
    Explanations

    section separators

    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
     Ranh
    -0.09
    indelijk
    -0.09
    ERIC
    -0.09
    trica
    -0.09
    ënt
    -0.08
    benh
    -0.08
     Ouver
    -0.08
    inals
    -0.08
     Erkrank
    -0.08
    igin
    -0.08
    POSITIVE LOGITS
    s
    0.10
    ات
    0.08
    0.07
    æĹ
    0.07
    æĭħ
    0.06
    --
    0.06
     I
    0.06
    atism
    0.06
    at
    0.05
     Lim
    0.05
    Activations Density 0.004%

    No Known Activations