© 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. 45269
    Prev
    Next
    INDEX
    Explanations

    idempotent / potent / projections

    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
    borne
    -0.08
    天çĽĸ
    -0.08
    puter
    -0.08
    Ñĩиков
    -0.08
    ombies
    -0.08
    epage
    -0.08
    enticated
    -0.08
    ços
    -0.07
    åħįè´¹åıijå¸ĥ
    -0.07
    æľīå¿ĥ人
    -0.07
    POSITIVE LOGITS
    otent
    0.08
    CCI
    0.07
    ouncy
    0.07
    emis
    0.06
    ansi
    0.06
    à¸ģิ
    0.06
    anson
    0.06
    /dis
    0.06
    ä¸įå¹²
    0.06
    ä¸įåĬ¨
    0.06
    Activations Density 0.003%

    No Known Activations