© 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. 24030
    Prev
    Next
    INDEX
    Explanations

    Australian hospital, murine, short-term implants, larger ones, solid state, rat hypothalamus, Wisconsin state, grassland species, animal genomes, human brain

    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
    äºijå³°
    -0.07
    /moment
    -0.07
    à¸ķีà¸Ļ
    -0.07
    poses
    -0.06
    对ä¸Ń
    -0.06
    ÙĩاÙĨ
    -0.06
     sfor
    -0.06
    ظÙĬÙģ
    -0.06
    ToEnd
    -0.06
     scop
    -0.06
    POSITIVE LOGITS
    ichen
    0.07
    icen
    0.07
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    0.07
    -style
    0.07
    èĢĥçĶŁçļĦ
    0.07
    oric
    0.07
    ×ķש
    0.06
    æĦıä¹īä¸ĬçļĦ
    0.06
    ildo
    0.06
    ä»»ä½ķä¸Ģ个
    0.06
    Activations Density 0.673%

    No Known Activations