© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21315
    Prev
    Next
    INDEX
    Explanations

    .Fatal verification

    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
    .tie
    -0.07
    çŃ
    -0.06
    大ä¼ļ
    -0.06
    _reserve
    -0.06
    åĨħ容çĶ±
    -0.06
    è½»éĩį
    -0.06
    urat
    -0.06
    å½¢åĬ¿
    -0.06
    æħĪ
    -0.06
    大æľī
    -0.06
    POSITIVE LOGITS
    expected
    0.12
    é¢ĦæľŁ
    0.12
    .expected
    0.11
     expected
    0.11
     Expected
    0.11
    é¢ĦæľŁçļĦ
    0.11
    Expected
    0.11
     erwart
    0.10
    .expect
    0.10
    Assert
    0.10
    Activations Density 0.204%

    No Known Activations