© 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. 11456
    Prev
    Next
    INDEX
    Explanations

    system configuration or expectations

    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
    omor
    -0.07
     gamb
    -0.07
    quam
    -0.07
    obet
    -0.07
    agé
    -0.07
    éĺ³åħīä¸ĭ
    -0.07
    å¿Ĩ
    -0.06
    ç°ĩ
    -0.06
    .neg
    -0.06
    asz
    -0.06
    POSITIVE LOGITS
     expects
    0.08
     expecting
    0.08
    èĢĥæł¸
    0.08
    _expected
    0.07
     expect
    0.07
    .require
    0.07
    éĺħåį·
    0.07
     tests
    0.07
    åİī
    0.07
    iche
    0.07
    Activations Density 0.025%

    No Known Activations