© 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. 4246
    Prev
    Next
    INDEX
    Explanations

    using a question

    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
    fol
    -0.07
    ãn
    -0.07
    itol
    -0.07
    å¤§åľ£
    -0.07
    odos
    -0.07
    ²
    -0.06
    oler
    -0.06
    ardon
    -0.06
     thôi
    -0.06
    icino
    -0.06
    POSITIVE LOGITS
    arro
    0.08
     overly
    0.07
    æķı
    0.07
    éĪ´
    0.07
     excessively
    0.07
    åģ¶
    0.07
    رÙĬد
    0.07
    Anything
    0.07
    à¸Īà¸ĩ
    0.07
     period
    0.07
    Activations Density 0.041%

    No Known Activations