© 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. 57969
    Prev
    Next
    INDEX
    Explanations

    `pre` code blocks

    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
    磼
    -0.08
    udge
    -0.07
    à§ĭধ
    -0.07
    éħİ
    -0.07
    ä¸įåĢ¼
    -0.07
    ucha
    -0.07
    æľīåı¯èĥ½æĺ¯
    -0.07
     "=",
    -0.07
    aju
    -0.07
    views
    -0.07
    POSITIVE LOGITS
    _scheme
    0.08
    éĺħ读åİŁæĸĩ
    0.07
    cire
    0.07
     Pratt
    0.06
    çĪ±ä¸įéĩĬ
    0.06
     pattern
    0.06
    éĩijæĸ¯
    0.06
    attan
    0.06
    modus
    0.06
    rex
    0.06
    Activations Density 0.043%

    No Known Activations