© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 18115
    Prev
    Next
    INDEX
    Explanations

    concluding transition

    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
    æīĢ以çİ°åľ¨
    -0.09
    ä»İèĢĮæıIJé«ĺ
    -0.09
    éĤ£åı¯
    -0.08
    çĦ¶åIJİçĤ¹åĩ»
    -0.08
    éĤ£ä½łå°±
    -0.08
    éĤ£æĪijå°±
    -0.08
    æīĢ以就
    -0.08
    éĤ£ä¹Īä½ł
    -0.08
    æīĢ以ä»ĸ们
    -0.07
    éĤ£æĺ¯åĽłä¸º
    -0.07
    POSITIVE LOGITS
    forth
    0.14
    ÑĬ
    0.10
    że
    0.09
    fter
    0.09
    iveness
    0.09
    oner
    0.09
    iasm
    0.09
    ä¹İ
    0.09
    -called
    0.09
    ê¹IJ
    0.08
    Activations Density 0.020%

    No Known Activations