© 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. 62212
    Prev
    Next
    INDEX
    Explanations

    logic, context, classic

    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
    èĩ³ä»Ĭå·²æľī
    -0.09
    å¥ĩèīº
    -0.09
    REFERENCES
    -0.09
     citar
    -0.08
    ialias
    -0.08
    åı·æĸĩ件
    -0.08
    PUTE
    -0.08
    /renderer
    -0.08
    uteurs
    -0.08
    upun
    -0.08
    POSITIVE LOGITS
    éĢ»è¾ij
    0.10
     logically
    0.09
     wording
    0.09
     logic
    0.09
     logical
    0.09
     semantics
    0.08
    çļĦéĢ»è¾ij
    0.08
     conditional
    0.08
     semantic
    0.07
    è¯Ńä¹ī
    0.07
    Activations Density 0.012%

    No Known Activations