© 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. 60924
    Prev
    Next
    INDEX
    Explanations

    specific traits or characteristics

    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
    otov
    -0.09
    å¤įåĪ¶æĪĸ
    -0.08
    ÑĤоÑĢ
    -0.08
    udou
    -0.08
    alet
    -0.07
    azón
    -0.07
    æĽ´åģ¥åº·
    -0.07
    æ¯Ķ以å¾Ģ
    -0.07
    éĢ»è¾ij
    -0.07
    ãĥķãĤ¡ãĥ¼
    -0.07
    POSITIVE LOGITS
    0.06
    åĽłåħ¶
    0.06
    èĢĮå¾ĹåIJį
    0.06
    度é«ĺ
    0.06
     its
    0.06
     (~
    0.06
    eful
    0.06
    zg
    0.05
    èĭ
    0.05
    (*)(
    0.05
    Activations Density 0.570%

    No Known Activations