© 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. 44460
    Prev
    Next
    INDEX
    Explanations

    album titles or beginnings

    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
     hypo
    -0.07
    _EXTRA
    -0.06
    çŁ¢
    -0.06
    lect
    -0.06
    xic
    -0.06
    isz
    -0.06
    ach
    -0.06
    çľĭ书
    -0.06
    æ±ĩ
    -0.06
    ypo
    -0.06
    POSITIVE LOGITS
    -prepend
    0.09
    zer
    0.09
    åĽ£
    0.08
    ignon
    0.08
     unnamed
    0.08
    ayer
    0.08
    onha
    0.07
    emouth
    0.07
    reck
    0.07
    unta
    0.07
    Activations Density 0.408%

    No Known Activations