© 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. 34694
    Prev
    Next
    INDEX
    Explanations

    "explain" followed by "Read"

    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
    åºĵéĩĮ
    -0.08
    lau
    -0.08
    ĵĺ
    -0.08
    agrid
    -0.08
    assin
    -0.08
    æīĵåİĭ
    -0.08
    åħŃåIJĪ
    -0.07
    ÏĦÏį
    -0.07
    irut
    -0.07
    bery
    -0.07
    POSITIVE LOGITS
    æĶ¯éħį
    0.08
    å®ļ
    0.07
     forts
    0.07
    å¥ī
    0.06
    æĭ¿
    0.06
    eis
    0.06
     Svens
    0.06
     essentially
    0.06
     algorithm
    0.06
     SORT
    0.06
    Activations Density 0.007%

    No Known Activations