© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15933
    Prev
    Next
    INDEX
    Explanations

    longer shots

    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
    åĸµ
    -0.08
     ouver
    -0.07
    åħ¬å¼ĢçļĦ
    -0.07
    uÅŁ
    -0.07
    arty
    -0.07
    ëįĺ
    -0.07
    neau
    -0.06
    .examples
    -0.06
    åݦ
    -0.06
    æ³ī
    -0.06
    POSITIVE LOGITS
    zos
    0.06
     perhaps
    0.06
    çİĭéĩij
    0.06
     stessi
    0.06
    ToLocal
    0.06
     Feliz
    0.06
    ardin
    0.06
    anky
    0.06
    zipcode
    0.06
    atab
    0.06
    Activations Density 0.086%

    No Known Activations