© 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. 64391
    Prev
    Next
    INDEX
    Explanations

    derivatives and partial derivatives

    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
    ç¥ĸ
    -0.07
    reen
    -0.07
    æ¢
    -0.06
    æĪĪå£ģ
    -0.06
    asso
    -0.06
    uddin
    -0.06
    çĶŁæķĪ
    -0.06
     عادÙĦ
    -0.06
    awan
    -0.06
    åŁºæĸ¯åĿ¦
    -0.06
    POSITIVE LOGITS
    ØŃÙĦ
    0.08
    à¹Ģà¸ī
    0.08
    SHOT
    0.07
    ä¸īæ±Ł
    0.07
    hone
    0.06
    ä¸īåįģåħŃ
    0.06
    eker
    0.06
    mist
    0.06
    äºĨæĮĩ
    0.06
    ply
    0.06
    Activations Density 0.009%

    No Known Activations