© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50192
    Prev
    Next
    INDEX
    Explanations

    examples below

    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
    adan
    -0.07
    ¬ģ
    -0.07
    anh
    -0.07
    TRANS
    -0.06
    abet
    -0.06
    DS
    -0.06
    olf
    -0.06
    udes
    -0.06
    SHOT
    -0.06
    Ñģан
    -0.06
    POSITIVE LOGITS
    æĢª
    0.08
    chimp
    0.08
    amik
    0.07
    è¿ĺåŃĺåľ¨
    0.07
     whatever
    0.07
    iaux
    0.07
    frau
    0.07
     Luh
    0.07
    affe
    0.07
    åħ¶ä¸Ń以
    0.07
    Activations Density 0.151%

    No Known Activations