© 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. 47017
    Prev
    Next
    INDEX
    Explanations

    all possible

    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
    èĬĤèĬĤ
    -0.07
    绣ä¸Ģ管çIJĨ
    -0.07
    oes
    -0.07
     focus
    -0.07
    olla
    -0.07
    å¿Ĺæĺİ
    -0.07
     Freitas
    -0.06
    è´µåľ¨
    -0.06
     absence
    -0.06
     Grote
    -0.06
    POSITIVE LOGITS
     possible
    0.13
    åı¯èĥ½çļĦ
    0.12
     conceivable
    0.10
    possible
    0.10
     posible
    0.10
     imaginable
    0.10
     Possible
    0.10
     possibile
    0.09
     možné
    0.09
     possÃŃvel
    0.09
    Activations Density 0.020%

    No Known Activations