© 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. 47227
    Prev
    Next
    INDEX
    Explanations

    stress leading to or followed by certain words

    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
    ÑģÑĤво
    -0.10
    и
    -0.09
    å°Ķå¾·
    -0.09
    WARDS
    -0.08
    ï¸ı
    -0.08
    好å¤ĦçļĦ
    -0.08
    stairs
    -0.08
    ÑģÑĤва
    -0.07
    serter
    -0.07
    heid
    -0.07
    POSITIVE LOGITS
    andard
    0.10
    cape
    0.09
    umpf
    0.08
    uous
    0.08
    andalone
    0.08
    ful
    0.08
    uji
    0.08
    ur
    0.07
    rieg
    0.07
    اء
    0.07
    Activations Density 0.016%

    No Known Activations