© 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. 50825
    Prev
    Next
    INDEX
    Explanations

    local, localized, boundary, focal

    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
     Brass
    -0.08
    utter
    -0.07
     instrument
    -0.07
     matrimoniale
    -0.07
    Instrument
    -0.07
    ç¯Ģ缮
    -0.07
    èĬ±èĮ¶
    -0.06
     Singles
    -0.06
    oku
    -0.06
    ertoire
    -0.06
    POSITIVE LOGITS
     locally
    0.09
    å±Ģéĥ¨
    0.08
    veau
    0.08
     boundary
    0.08
    æī©æķ£
    0.07
     focal
    0.07
     localized
    0.07
    çīĩåĮº
    0.07
    沧
    0.07
     neighborhoods
    0.07
    Activations Density 0.028%

    No Known Activations