© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    John Doe

    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
    彩äºij
    -0.07
    sil
    -0.07
    æĬ¤çIJĨè´¹
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    ä¿Ĭ
    -0.06
    éŀĺ
    -0.06
    eled
    -0.06
     Reisen
    -0.06
    attoo
    -0.06
     Aug
    -0.06
    POSITIVE LOGITS
    _hello
    0.09
    示ä¾ĭ
    0.09
    >Lorem
    0.08
    èĻļæŀĦ
    0.08
    eldon
    0.08
    ä¾ĭåŃIJ
    0.08
    arb
    0.08
    .example
    0.07
     Scenario
    0.07
    ç¬ijç¬ij
    0.07
    Activations Density 0.546%

    No Known Activations