© 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. 8407
    Prev
    Next
    INDEX
    Explanations

    organization, education, aid, fed, fuel

    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
    они
    -0.08
    utup
    -0.08
    еÑĢбÑĥ
    -0.08
    sak
    -0.08
    uken
    -0.08
    procs
    -0.08
    ële
    -0.08
    ÑģлÑĮ
    -0.07
    ’S
    -0.07
    yas
    -0.07
    POSITIVE LOGITS
    ings
    0.08
    Ĭ
    0.08
    Ĥ
    0.07
    ighbour
    0.07
    ungs
    0.06
     "
    0.06
    ling
    0.06
    تÛĮ
    0.06
     (
    0.06
    nce
    0.06
    Activations Density 0.015%

    No Known Activations