© 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. 59077
    Prev
    Next
    INDEX
    Explanations

    movie/show titles

    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
    Negative Logits
    å°ıçļĦæŶåĢĻ
    -0.06
    _tc
    -0.06
     fon
    -0.06
    naver
    -0.06
    rene
    -0.06
    举èĩ³
    -0.06
    åĽºæľī
    -0.05
    iks
    -0.05
    (?)
    -0.05
     limiting
    -0.05
    POSITIVE LOGITS
    ãĢĭ
    0.08
    orada
    0.08
    éĩİå¿ĥ
    0.08
    invert
    0.08
    çIJ¥
    0.08
    oces
    0.08
    iskon
    0.07
    arpa
    0.07
    UNT
    0.07
    airs
    0.07
    Activations Density 0.041%

    No Known Activations