© 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. 55274
    Prev
    Next
    INDEX
    Explanations

    post followed by suffixes

    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
    hart
    -0.09
    /her
    -0.09
    ÑĤÑģÑı
    -0.08
    åĭĥåĭĥ
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    zinho
    -0.07
    voud
    -0.07
     phá»ij
    -0.07
    zaam
    -0.07
    ously
    -0.07
    POSITIVE LOGITS
    erior
    0.13
    gresql
    0.11
    pone
    0.10
    ivity
    0.10
    gres
    0.10
    rophe
    0.09
    greSQL
    0.09
     facto
    0.09
    graduate
    0.09
    ively
    0.09
    Activations Density 0.103%

    No Known Activations