© 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. 62905
    Prev
    Next
    INDEX
    Explanations

    refer to figure/image/exhibit

    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
    ooter
    -0.08
    .mozilla
    -0.07
    âĹĩâĹĨ
    -0.07
    afety
    -0.07
    éĥİ
    -0.07
    iali
    -0.07
    æķĪçİĩé«ĺ
    -0.07
    nte
    -0.07
    alue
    -0.07
    uet
    -0.06
    POSITIVE LOGITS
    ä¹ĭåĬ¿
    0.08
    zinho
    0.07
    ez
    0.07
    geom
    0.07
    rend
    0.07
    skog
    0.07
    azed
    0.07
    reja
    0.06
     boc
    0.06
    ed
    0.06
    Activations Density 0.002%

    No Known Activations