© 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. 42477
    Prev
    Next
    INDEX
    Explanations

    strategy, maps, meetings, devices, routing

    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
    estes
    -0.08
    irman
    -0.08
    <small
    -0.08
    -Version
    -0.08
    vester
    -0.08
    asses
    -0.08
    avian
    -0.07
    alles
    -0.07
    -ves
    -0.07
    èĩĤ
    -0.07
    POSITIVE LOGITS
    /
    0.07
    çĶľé£Ł
    0.06
    acle
    0.06
    -
    0.06
    人家
    0.06
    nö
    0.06
     centered
    0.06
    L
    0.06
    è¿ĺåı¯ä»¥éĢļè¿ĩ
    0.06
    ogenic
    0.05
    Activations Density 0.415%

    No Known Activations