© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30100
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code variables

    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
    stage
    -0.07
    忱
    -0.07
    çľģå¤ĸ
    -0.07
    éĩįéĩij
    -0.07
    BIND
    -0.07
    -stage
    -0.06
    ä»·æł¼ä¸Ĭ涨
    -0.06
    .uint
    -0.06
     boob
    -0.06
    çĶ·åŃ©åŃIJ
    -0.06
    POSITIVE LOGITS
     ±
    0.11
     +/-
    0.11
     signed
    0.11
     (-
    0.11
    ([-
    0.11
     [-
    0.10
    ±
    0.10
     +-
    0.09
    (-
    0.09
    signed
    0.09
    Activations Density 0.040%

    No Known Activations