© 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. 1742
    Prev
    Next
    INDEX
    Explanations

    assuming positive

    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
    رØŃ
    -0.09
    ignée
    -0.08
     $("#"
    -0.07
     (!!
    -0.07
    é¹Ĭ
    -0.07
    bish
    -0.07
    ç¶
    -0.07
    izr
    -0.07
    çŃĽ
    -0.07
    sov
    -0.07
    POSITIVE LOGITS
     variables
    0.09
     inputs
    0.08
    åıĺéĩı
    0.08
     values
    0.08
     Inputs
    0.08
    Variables
    0.08
     ë³ĢìĪĺ
    0.08
    å°¼æĸ¯
    0.07
    inputs
    0.07
     positive
    0.07
    Activations Density 0.006%

    No Known Activations