© 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. 28003
    Prev
    Next
    INDEX
    Explanations

    file types and data structures

    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
    AndUpdate
    -0.08
    Cls
    -0.07
    ascar
    -0.07
    eneg
    -0.07
    Framework
    -0.07
     neum
    -0.07
     einger
    -0.07
    Override
    -0.07
    ä¸įçł´
    -0.07
    czÄħ
    -0.07
    POSITIVE LOGITS
     resulting
    0.09
    ä¸įèī¯å½±åĵį
    0.09
    _rw
    0.07
    æĥ³è¦ģ
    0.07
    ture
    0.07
     daraus
    0.07
    hasil
    0.07
    åĩºåİ»
    0.07
    å°Ĩä»İ
    0.07
    REQUIRED
    0.07
    Activations Density 1.011%

    No Known Activations