© 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. 24270
    Prev
    Next
    INDEX
    Explanations

    finding closest/biggest/smallest value

    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
    udi
    -0.09
    udy
    -0.08
    erule
    -0.07
    udu
    -0.07
    çİ°åľºçļĦ
    -0.07
    agar
    -0.07
    à§Ī
    -0.07
     trôi
    -0.07
    pector
    -0.07
    elay
    -0.06
    POSITIVE LOGITS
     neither
    0.08
    irit
    0.07
    Ïģαι
    0.07
    籤
    0.07
    å¿Ĺ强
    0.07
    apura
    0.07
     Neither
    0.07
    Geom
    0.07
    尼迪
    0.07
    ?p
    0.07
    Activations Density 0.016%

    No Known Activations