© 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. 13404
    Prev
    Next
    INDEX
    Explanations

    money

    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
    sWith
    -0.10
    ï¸İ
    -0.10
    ients
    -0.10
    à¸ģารà¸ĵà¹Į
    -0.09
    wyczaj
    -0.09
    NullOr
    -0.08
    ively
    -0.08
    pecially
    -0.08
    олÑĮ
    -0.08
    reeze
    -0.08
    POSITIVE LOGITS
    ifest
    0.08
    icz
    0.08
     اÙĦØŃÙĬÙĪÙĬØ©
    0.07
    /time
    0.07
    melon
    0.07
    éĴ±
    0.07
    vern
    0.07
     raya
    0.07
    wiÅĽcie
    0.07
    -making
    0.07
    Activations Density 0.017%

    No Known Activations