© 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. 31540
    Prev
    Next
    INDEX
    Explanations

    per 100,000

    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
    åİŁä»¶åıĬ
    -0.07
    ucha
    -0.07
    ida
    -0.07
    æIJľéĽĨ
    -0.06
    yon
    -0.06
    æģķ
    -0.06
    æĶ¶éĽĨ
    -0.06
    bron
    -0.06
    ellini
    -0.06
    ãģ¤ãģį
    -0.06
    POSITIVE LOGITS
    Del
    0.08
    æİĤ
    0.07
    åıĤä¸İè¯Ħ论
    0.07
    éłĵ
    0.07
    unami
    0.07
     Ю
    0.07
    ä½ķçŃī
    0.07
    fore
    0.07
    Fore
    0.07
    dbh
    0.07
    Activations Density 0.002%

    No Known Activations