© 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. 44127
    Prev
    Next
    INDEX
    Explanations

    normal subgroup question

    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
    çĤ¹æķ°
    -0.07
    éĢ¼äºº
    -0.07
     Daly
    -0.07
    åĪ°çĽ®åīį
    -0.06
    andes
    -0.06
    ampa
    -0.06
    apper
    -0.06
    赤
    -0.06
    okok
    -0.06
     spr
    -0.06
    POSITIVE LOGITS
    ugat
    0.08
    opedia
    0.07
    iff
    0.07
    oy
    0.07
    unt
    0.07
    ²
    0.07
    adar
    0.07
    ('__
    0.07
    hin
    0.07
    åľ¨åħ¨
    0.07
    Activations Density 0.006%

    No Known Activations