© 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. 43444
    Prev
    Next
    INDEX
    Explanations

    ctype, Boom

    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
    udel
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ä¼ĺç§Ģå¥ĸ
    -0.07
    Ả
    -0.07
    åıĬ产åĵģ
    -0.07
     convention
    -0.07
    åħĪåİ»
    -0.07
    arit
    -0.07
    ftware
    -0.07
    Cli
    -0.07
    POSITIVE LOGITS
    åħ¬åħ±
    0.07
    ç¾¤å²Ľ
    0.06
    uhkan
    0.06
    æ¶Ľ
    0.06
    usan
    0.06
    é¡ı
    0.06
    å½Ĵ宿
    0.06
    å¦Ĥä½ķå°Ĩ
    0.06
    æ°¸è¿ľçļĦ
    0.06
    _TRACK
    0.06
    Activations Density 0.035%

    No Known Activations