© 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. 4911
    Prev
    Next
    INDEX
    Explanations

    want team

    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
    lord
    -0.07
    èijĨ
    -0.06
    ssp
    -0.06
    edan
    -0.06
    icule
    -0.06
    ove
    -0.06
    大æ³ķ
    -0.06
    erven
    -0.06
    åºĶåħ·å¤ĩ
    -0.06
    .divide
    -0.06
    POSITIVE LOGITS
    ença
    0.07
    гол
    0.07
    wegen
    0.07
     interc
    0.07
    ceria
    0.07
     далÑĮ
    0.07
    гнÑĥ
    0.07
    ./.
    0.07
    ר×Ķ
    0.07
    esak
    0.07
    Activations Density 0.004%

    No Known Activations