© 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. 9230
    Prev
    Next
    INDEX
    Explanations

    rebuild, Reform, networks, Act, Serializer, earned, stage

    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
     ([[
    -0.09
    zi
    -0.08
    å±ħæĺĵ
    -0.08
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    -0.07
    enza
    -0.07
     simplific
    -0.07
    ##_
    -0.07
    fic
    -0.07
    ç±į
    -0.07
    ä»ĭ
    -0.07
    POSITIVE LOGITS
     ï¿¥
    0.07
    并已
    0.07
    ä¸Ķåľ¨
    0.07
    Ñıд
    0.06
    iores
    0.06
    lebt
    0.06
    æŁIJ
    0.06
    yas
    0.06
     paid
    0.06
    гÑĢан
    0.06
    Activations Density 0.288%

    No Known Activations