© 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. 33608
    Prev
    Next
    INDEX
    Explanations

    index, score, reaches

    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
    onical
    -0.08
    Indent
    -0.08
    _tA
    -0.07
    天å®ī
    -0.07
    æĿ¥åķ¦
    -0.07
    angk
    -0.07
    TURE
    -0.07
    ught
    -0.07
    tida
    -0.07
    :/
    -0.07
    POSITIVE LOGITS
    è¾¾æĸ¯
    0.08
    è¾¾åħĭ
    0.08
    对åºĶ
    0.08
    æĺłå°Ħ
    0.08
     mapped
    0.08
    uster
    0.07
    æ¾Ħ
    0.07
    æ±Łè·¯
    0.07
    uff
    0.07
    åħĭ
    0.07
    Activations Density 0.032%

    No Known Activations