© 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. 12854
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    entas
    -0.09
    CRI
    -0.07
    ç»İ
    -0.07
    xca
    -0.07
    íķĺëĭĪ
    -0.07
    rets
    -0.07
     desar
    -0.07
    onas
    -0.07
    trys
    -0.07
    å²ij
    -0.07
    POSITIVE LOGITS
    ixer
    0.08
    éªĦ
    0.07
    å½ĵçĦ¶
    0.07
    æĪĸèĢħ
    0.07
     Weiner
    0.07
    or
    0.07
    åIJĮæŶ
    0.07
    åį³
    0.07
    çĶļèĩ³åľ¨
    0.06
    orit
    0.06
    Activations Density 0.013%

    No Known Activations