© 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. 62679
    Prev
    Next
    INDEX
    Explanations

    initiating or initiated

    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
    ewise
    -0.07
    身åīį
    -0.06
    grab
    -0.06
    èŀįéĢļ
    -0.06
    .native
    -0.06
    gre
    -0.06
    éķ¿æľŁ
    -0.06
    ersh
    -0.06
    éĺ¶
    -0.06
    没æľī帮åĬ©
    -0.06
    POSITIVE LOGITS
    带åĬ¨
    0.09
    deaux
    0.09
    带åĬ¨ä¸ĭ
    0.09
    ipple
    0.08
    带åĬ¨äºĨ
    0.08
     Initi
    0.08
     initiating
    0.08
     Gund
    0.08
    paque
    0.07
    _init
    0.07
    Activations Density 0.101%

    No Known Activations