© 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. 10217
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
    ãģ³
    -0.08
    æ»ŀ
    -0.08
    ond
    -0.08
    à¸Ĩ
    -0.08
    QUIS
    -0.07
    ivit
    -0.07
    iosi
    -0.07
    çĶŁç´ł
    -0.07
    chl
    -0.07
    ]+"
    -0.07
    POSITIVE LOGITS
    utenberg
    0.07
    Directions
    0.07
    unce
    0.07
    å¯Į强
    0.06
    æŀģ大çļĦ
    0.06
     namespace
    0.06
    ÙĪÙĦÙĬÙĨ
    0.06
     carr
    0.06
    Boston
    0.06
    _DECL
    0.06
    Activations Density 0.003%

    No Known Activations