© 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. 58799
    Prev
    Next
    INDEX
    Explanations

    punctuation and clause endings

    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
    atham
    -0.07
    çĶ±äºİåħ¶
    -0.07
    为己
    -0.07
    conto
    -0.06
    以çĤº
    -0.06
    为éģ¿åħį
    -0.06
    以为
    -0.06
    Åĵ
    -0.06
    fstream
    -0.06
    ÐŁÐIJ
    -0.06
    POSITIVE LOGITS
    çĦ¶å¤§
    0.08
    ibaba
    0.07
    ilien
    0.07
    ppet
    0.07
    èĢĮä¸Ķè¦ģ
    0.07
    ARING
    0.07
    undra
    0.07
    åı¤å±ĭ
    0.07
    opter
    0.07
    ikal
    0.07
    Activations Density 0.082%

    No Known Activations