© 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. 876
    Prev
    Next
    INDEX
    Explanations

    subtype A, VIIB submarines, ε4 allele, nornicotine

    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
    atical
    -0.08
    æŃ»ä¸į
    -0.07
    å½ĵçĦ¶æĺ¯
    -0.07
    VT
    -0.07
    ABS
    -0.06
    ique
    -0.06
    æĹłéĺ»
    -0.06
     Maggi
    -0.06
    cation
    -0.06
    tern
    -0.06
    POSITIVE LOGITS
     föl
    0.08
    mh
    0.08
    ippy
    0.08
    idor
    0.07
     Huffington
    0.07
    tparam
    0.07
    åĵ©
    0.07
    aren
    0.07
    åIJĮä¸Ĭ
    0.07
     accompany
    0.07
    Activations Density 0.027%

    No Known Activations