© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21709
    Prev
    Next
    INDEX
    Explanations

    Channel News

    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
    apos
    -0.07
    itin
    -0.07
    .mit
    -0.07
    Tower
    -0.07
     dictator
    -0.07
    éļIJ身
    -0.06
    asca
    -0.06
     Counsel
    -0.06
    ital
    -0.06
    eter
    -0.06
    POSITIVE LOGITS
    å§ĭèĩ³
    0.08
    ubin
    0.07
     Outre
    0.07
    aih
    0.07
    åĬ©
    0.07
     menyar
    0.07
    окÑģи
    0.07
    究
    0.07
     appendString
    0.07
    onders
    0.06
    Activations Density 1.103%

    No Known Activations