© 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. 46140
    Prev
    Next
    INDEX
    Explanations

    organizational or legal context

    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
    izzi
    -0.08
    رائ
    -0.08
    ope
    -0.08
    undle
    -0.08
    æľĢæĸ°è¯Ħ论
    -0.07
    esor
    -0.07
    æŃ»çļĦ
    -0.07
    ucar
    -0.07
    Drv
    -0.07
    piel
    -0.07
    POSITIVE LOGITS
    µ
    0.07
     namely
    0.07
    ¶
    0.07
    å¥
    0.06
    nam
    0.06
     []).
    0.06
     infatti
    0.06
    äºĶåĪĨ
    0.06
    CID
    0.06
    ÙĦاÙĭ
    0.06
    Activations Density 0.048%

    No Known Activations