© 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. 38624
    Prev
    Next
    INDEX
    Explanations

    official actions and descriptions

    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
    avn
    -0.07
    ynn
    -0.06
    ucc
    -0.06
    åħĥæ°Ķ
    -0.06
    å°Ķ
    -0.06
    unga
    -0.06
    æĪĴ
    -0.05
    és
    -0.05
    å¿ĥ
    -0.05
     Kendall
    -0.05
    POSITIVE LOGITS
    engen
    0.09
    สุà¸Ķà¸Ĺà¹īาย
    0.08
    ît
    0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
    umann
    0.08
    设为é¦ĸ页
    0.08
    еÑħ
    0.08
     ÑĢазнов
    0.08
    urdy
    0.08
    çŃĶ主
    0.08
    Activations Density 0.065%

    No Known Activations