© 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. 34471
    Prev
    Next
    INDEX
    Explanations

    Kelly, Movie, Camera, Radar, Lost

    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
    åıĪä½ķ
    -0.07
    ircraft
    -0.07
    els
    -0.07
    à®®à¯Ī
    -0.07
    elize
    -0.07
    addir
    -0.07
    ############
    -0.07
     domic
    -0.07
    åĨįéĢł
    -0.07
     Lumi
    -0.07
    POSITIVE LOGITS
    owing
    0.08
    Ĭ
    0.08
    енÑĮ
    0.08
    .|
    0.07
    arity
    0.07
    oš
    0.07
    anders
    0.07
    aat
    0.07
    angu
    0.07
     |
    0.07
    Activations Density 0.023%

    No Known Activations