© 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. 16600
    Prev
    Next
    INDEX
    Explanations

    Let assignment

    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
    åıįè¦Ĩ
    -0.08
    ä»»æĢ¨
    -0.07
    ðŁĺĢ
    -0.07
    èĩªåį«
    -0.07
    çł²
    -0.07
    åĽī
    -0.07
    åıĤåĬłä¼ļè®®
    -0.07
    åħ¼
    -0.07
    å¦ĤçĥŁ
    -0.07
     UNIX
    -0.06
    POSITIVE LOGITS
    æ£ł
    0.07
    à¸ķร
    0.07
    å°ıé¢ĺ
    0.07
    å¥Ĺé¤IJ
    0.07
    alise
    0.07
    हार
    0.07
    cki
    0.07
    chez
    0.07
    aglio
    0.07
    uite
    0.07
    Activations Density 0.032%

    No Known Activations