© 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. 62921
    Prev
    Next
    INDEX
    Explanations

    rootograms

    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
    浩
    -0.08
    ç¼ķ
    -0.07
    人åİ»
    -0.07
    巨大çļĦ
    -0.06
    èĢĥ究
    -0.06
    onger
    -0.06
    çħ§
    -0.06
     "}
    -0.06
    uper
    -0.06
     totaled
    -0.06
    POSITIVE LOGITS
    éĻĦè¿ijçļĦ
    0.10
    éĻĦè¿ijæľī
    0.09
    éĻĦè¿ij
    0.09
     vicinity
    0.08
    éĢ¼è¿ij
    0.08
    Iterations
    0.08
     locating
    0.08
     approximate
    0.08
    åıijçİ°çļĦ
    0.07
     nearby
    0.07
    Activations Density 0.010%

    No Known Activations