© 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. 46310
    Prev
    Next
    INDEX
    Explanations

    give q

    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
     Bris
    -0.09
    太大äºĨ
    -0.08
    å°ıå¹³
    -0.08
    itano
    -0.08
    _TRY
    -0.08
    对ä¸ĢäºĽ
    -0.08
    olos
    -0.08
    ieven
    -0.08
    athing
    -0.07
    iliar
    -0.07
    POSITIVE LOGITS
    笼
    0.07
    zah
    0.07
    ÑĢок
    0.07
    HCM
    0.06
     dll
    0.06
    åĪĩ
    0.06
    çļ®
    0.06
    .hl
    0.06
    éħį
    0.06
    该çīĩ
    0.06
    Activations Density 0.375%

    No Known Activations