© 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. 11921
    Prev
    Next
    INDEX
    Explanations

    substitution and transformation

    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
    lyn
    -0.08
    нок
    -0.07
    inken
    -0.07
    çĿĢæĪij们çļĦ
    -0.07
    äºİä¸Ģ身
    -0.07
    hya
    -0.07
    çļĦè¡Į为
    -0.07
    leness
    -0.07
    øs
    -0.07
    ноÑģ
    -0.07
    POSITIVE LOGITS
     transformation
    0.10
     transformations
    0.09
    åıĺéĩı
    0.08
    owitz
    0.08
    åıĺæį¢
    0.08
     transforms
    0.08
     transforma
    0.08
    -transform
    0.08
    Transform
    0.08
     Transform
    0.08
    Activations Density 0.009%

    No Known Activations