© 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. 29350
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ut
    -0.06
    lean
    -0.06
    acker
    -0.06
     vs
    -0.06
    ??
    -0.06
    çĶļèĩ³æĺ¯
    -0.06
    loc
    -0.06
    ?
    -0.06
    arc
    -0.06
    iller
    -0.06
    POSITIVE LOGITS
    емов
    0.08
    åij¨å²ģ以ä¸Ĭ
    0.08
    ä¸Ģè§ī
    0.08
    icional
    0.08
    oteca
    0.08
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.08
     sourceMappingURL
    0.08
    ungg
    0.08
    itionally
    0.08
    Activations Density 0.000%

    No Known Activations