© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 653
    Prev
    Next
    INDEX
    Explanations

    delete items

    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
    Negative Logits
    er
    -0.07
    era
    -0.07
    erro
    -0.06
    zer
    -0.06
     "
    -0.06
    ALI
    -0.06
     mun
    -0.06
    åİĨåİĨ
    -0.06
    oun
    -0.06
    ion
    -0.06
    POSITIVE LOGITS
    udeau
    0.09
    kost
    0.08
    ÏģεÏį
    0.08
    飶
    0.08
    åħ¨éĥ¨è¯Ħ论
    0.08
    ieden
    0.08
    plode
    0.08
    ailability
    0.08
    åıĤä¸İåĪ°
    0.08
    PEAR
    0.08
    Activations Density 0.014%

    No Known Activations