© 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. 13009
    Prev
    Next
    INDEX
    Explanations

    morphism, bracket, implicit, inject, perception

    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
    -0.07
     variable
    -0.06
    âĢ¦
    -0.06
    -0.06
    posed
    -0.06
    ä¸įèĥ½æľī
    -0.06
     replic
    -0.06
    orp
    -0.06
    æĭħå½ĵ
    -0.06
    æıIJåĩºè¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
    atsby
    0.09
    ondi
    0.09
    xDA
    0.08
    ruik
    0.08
    人æīĭ
    0.08
    _SWAP
    0.08
    å¤§æ±Ł
    0.08
    ILT
    0.08
    Insensitive
    0.08
    (Parse
    0.08
    Activations Density 0.007%

    No Known Activations