© 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. 21458
    Prev
    Next
    INDEX
    Explanations

    champion, final, position, last

    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
    åħĭåĬĽ
    -0.08
    tiers
    -0.08
    leur
    -0.08
     isNaN
    -0.08
    賦
    -0.08
    大åĪĢ
    -0.08
    umpang
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
    æµ®çĶŁ
    -0.07
    建åįİ
    -0.07
    POSITIVE LOGITS
     final
    0.12
    ç»ĵæĿŁæŶ
    0.11
     reached
    0.10
    _final
    0.10
    final
    0.10
    ç»ĪçĤ¹
    0.10
     finale
    0.10
    çļĦæľĢç»Ī
    0.10
    æľĢç»Ī
    0.10
     اÙĦÙĨÙĩائÙĬØ©
    0.10
    Activations Density 0.047%

    No Known Activations