© 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. 10547
    Prev
    Next
    INDEX
    Explanations

    in vitro

    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
    enf
    -0.06
    éħįæĪ´
    -0.06
    asuk
    -0.06
    enius
    -0.06
     ev
    -0.06
    jár
    -0.06
    红润
    -0.06
    omt
    -0.06
    åĿ¦çĦ¶
    -0.06
     Ashton
    -0.06
    POSITIVE LOGITS
    ©
    0.08
    éĿĴå¹´å¿ĹæĦ¿èĢħ
    0.07
    ear
    0.07
    åŁ¼
    0.07
    鲨
    0.07
    orsa
    0.07
    §
    0.07
    æ©ĺ
    0.07
    çIJĨæīĢ
    0.07
    cente
    0.07
    Activations Density 0.927%

    No Known Activations