© 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. 4695
    Prev
    Next
    INDEX
    Explanations

    running / selling

    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
    uration
    -0.12
    avanaugh
    -0.12
    ypes
    -0.11
    หมาย
    -0.09
    schild
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    eenth
    -0.08
    ами
    -0.08
    gether
    -0.08
    yped
    -0.08
    POSITIVE LOGITS
    er
    0.12
    æķĻäºİ
    0.09
    볬
    0.09
    oops
    0.08
    sted
    0.08
    ấp
    0.08
    rig
    0.08
    ame
    0.08
    iously
    0.08
    ä¸įçķħ
    0.08
    Activations Density 0.004%

    No Known Activations