© 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. 41083
    Prev
    Next
    INDEX
    Explanations

    of a compact

    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
    ighton
    -0.08
    lood
    -0.06
    agn
    -0.06
    åı£åŃIJ
    -0.06
    agni
    -0.06
    convert
    -0.06
     Ow
    -0.06
    ØŃÙĪÙĬÙĦ
    -0.06
    çĶ±æĶ¿åºľ
    -0.06
    bury
    -0.06
    POSITIVE LOGITS
    _UDP
    0.08
    åĪ©æĸ¯
    0.08
    Controls
    0.08
    Ïģια
    0.08
    à©
    0.07
    fdc
    0.07
    åħĭèIJ¨æĸ¯
    0.07
    finite
    0.07
     kew
    0.07
     finite
    0.07
    Activations Density 0.008%

    No Known Activations