© 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. 8386
    Prev
    Next
    INDEX
    Explanations

    policy to

    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
    aso
    -0.07
    ock
    -0.07
    anth
    -0.07
    群æĺŁ
    -0.07
    ersh
    -0.07
    ike
    -0.07
    å¸Ĥ缴
    -0.07
    ayo
    -0.07
    bió
    -0.07
    apesh
    -0.06
    POSITIVE LOGITS
    ĥģ
    0.10
    ocaly
    0.08
     writeTo
    0.07
     جÙĪر
    0.07
    erties
    0.07
    ä¸ŃæŬ
    0.07
    гам
    0.07
    ÑĩиÑı
    0.06
    adis
    0.06
    ffen
    0.06
    Activations Density 0.034%

    No Known Activations