© 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. 55831
    Prev
    Next
    INDEX
    Explanations

    code closing and cleanup

    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
    eens
    -0.08
    鸾
    -0.08
    è¦ģæīĵ
    -0.08
    oves
    -0.08
    =$((
    -0.07
    éľĢè¦ģåģļ
    -0.07
    豫
    -0.07
    setError
    -0.07
    è¦ģ注éĩį
    -0.07
    ove
    -0.07
    POSITIVE LOGITS
    åıĸèĢĮ代ä¹ĭ
    0.07
     Rat
    0.07
     Tau
    0.06
     exploited
    0.06
    sources
    0.06
    ixel
    0.06
     Returned
    0.06
    áĥĺáĥľ
    0.06
    .encode
    0.06
     femin
    0.06
    Activations Density 0.027%

    No Known Activations