© 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. 45772
    Prev
    Next
    INDEX
    Explanations

    ticket units

    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
    ä¾ĽéĶĢ
    -0.07
    ier
    -0.07
     fair
    -0.06
     Paulista
    -0.06
    夹å±Ĥ
    -0.06
    доÑĢов
    -0.06
    é©¾é©¶æľºåĬ¨è½¦
    -0.06
    ly
    -0.06
    æĬŀ
    -0.06
    amna
    -0.06
    POSITIVE LOGITS
    åħ¬
    0.08
    è¿ĩéĩį
    0.07
    alkan
    0.07
    allinen
    0.07
    /repository
    0.07
    è¿ĩéķ¿
    0.07
    æĿĢ伤
    0.07
    äºĨä¸ĢåĪĩ
    0.07
     tät
    0.07
    игÑĢа
    0.06
    Activations Density 0.001%

    No Known Activations