© 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. 63120
    Prev
    Next
    INDEX
    Explanations

    weather modification, guide, frequent, drug, writers, mission

    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
    客æľįçĥŃ线
    -0.08
    acus
    -0.07
    [âĢ¦
    -0.07
    [++
    -0.07
    innie
    -0.07
    illow
    -0.07
     [âĢ¦
    -0.07
    alendar
    -0.07
    [âĢ¦]
    -0.07
    ivic
    -0.07
    POSITIVE LOGITS
    ç¯ĩä¸Ģ
    0.09
    æľĢæĸ°æĸĩç«ł
    0.08
    TAG
    0.06
     buff
    0.06
    imal
    0.06
    æĥ¨åı«
    0.06
    &amp
    0.06
     Aby
    0.06
    ryp
    0.06
    rain
    0.06
    Activations Density 0.602%

    No Known Activations