© 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. 55246
    Prev
    Next
    INDEX
    Explanations

    Bourne

    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
    laut
    -0.07
    anse
    -0.07
    æĭ·
    -0.07
    gena
    -0.07
    让çĶŁæ´»
    -0.07
    ackbar
    -0.07
     برس
    -0.07
    .paper
    -0.07
    åĨįæİ¥
    -0.07
    ÛĮب
    -0.07
    POSITIVE LOGITS
    ķ
    0.07
    Yu
    0.07
    âĢIJ
    0.07
    hol
    0.06
    ngo
    0.06
    *X
    0.06
    ugin
    0.06
    ingo
    0.06
    ä¸į欲
    0.06
    Tau
    0.06
    Activations Density 0.002%

    No Known Activations