© 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. 61109
    Prev
    Next
    INDEX
    Explanations

    decreased quantities or levels

    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
     (++
    -0.09
    ++
    -0.08
    æī©å¤§
    -0.08
    (++
    -0.07
    æĺĤé¦ĸ
    -0.07
    太éĩį
    -0.07
    è¶ħéĩį
    -0.07
    å¢ŀ
    -0.07
    ++;
    -0.07
    å¾Īéĩį
    -0.07
    POSITIVE LOGITS
     diminished
    0.15
     fewer
    0.15
     decreased
    0.15
    åĩıå°ij
    0.14
    è¶ĬæĿ¥è¶Ĭå°ij
    0.14
     reduced
    0.14
    è¿ľä½İäºİ
    0.14
    éĻįèĩ³
    0.14
     dwind
    0.13
    åĩıå°ijäºĨ
    0.13
    Activations Density 0.154%

    No Known Activations