© 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. 7231
    Prev
    Next
    INDEX
    Explanations

    code paths and names

    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
    abis
    -0.08
    æı
    -0.07
    wers
    -0.07
    erlo
    -0.07
    apons
    -0.07
    hdr
    -0.06
    apl
    -0.06
    oth
    -0.06
    Ñģл
    -0.06
    Ñģко
    -0.06
    POSITIVE LOGITS
    èŤ
    0.08
    [table
    0.07
    缸å¾ħ
    0.07
    æĪijä¸įè¦ģ
    0.07
    çĮķçĮ´æ¡ĥ
    0.07
    .ld
    0.07
    idge
    0.07
    æĺ¯å°ı
    0.07
    ecker
    0.07
     poż
    0.07
    Activations Density 0.023%

    No Known Activations