© 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. 7161
    Prev
    Next
    INDEX
    Explanations

    required, non-null, presence

    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
    ëŀij
    -0.08
    ilver
    -0.08
    tava
    -0.08
    cala
    -0.07
     NotImplemented
    -0.07
    HING
    -0.07
    -cr
    -0.07
    riet
    -0.07
    Radians
    -0.07
    ubits
    -0.07
    POSITIVE LOGITS
    æľĢå°ij
    0.09
    èĩ³å°ij
    0.08
    èµ·çłģ
    0.08
    å¿ħé¡»æľī
    0.08
     mandatory
    0.08
    ä¸įå°ijäºİ
    0.08
    .Required
    0.08
     minimum
    0.08
    nonnull
    0.08
    NotEmpty
    0.08
    Activations Density 0.010%

    No Known Activations