© 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. 56290
    Prev
    Next
    INDEX
    Explanations

    her/hereditary/hermetic

    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
    nya
    -0.09
    s
    -0.09
    ness
    -0.08
    ãģĦãĤĭ
    -0.07
    翼翼
    -0.07
    enticate
    -0.07
    اÙĭ
    -0.07
    ique
    -0.07
    mente
    -0.07
    о
    -0.07
    POSITIVE LOGITS
    editary
    0.18
    zelfde
    0.16
    esy
    0.16
    -même
    0.14
    zelf
    0.14
    etical
    0.13
    èĢģ人家
    0.11
    /her
    0.11
    metic
    0.10
    ffield
    0.10
    Activations Density 0.099%

    No Known Activations