© 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. 50156
    Prev
    Next
    INDEX
    Explanations

    HTML tags, code, type definitions

    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
    lik
    -0.07
    ere
    -0.06
    bund
    -0.06
    Ke
    -0.06
     Ste
    -0.06
    atin
    -0.06
    åıĽéĢĨ
    -0.06
    ä¸įåIJĮçļĦ
    -0.06
     Ke
    -0.06
    ebbe
    -0.06
    POSITIVE LOGITS
    odef
    0.10
    itage
    0.09
    orest
    0.08
    çī©è¯Ń
    0.08
    æĪĸæľª
    0.08
    ç¡ķ士çĶŁ
    0.08
    önen
    0.08
    tober
    0.08
    unner
    0.08
    IRTUAL
    0.08
    Activations Density 0.007%

    No Known Activations