© 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. 49662
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
    åŃĺ
    -0.07
    omod
    -0.06
     hur
    -0.06
    ä¸įæĢĿ
    -0.06
    æĮģ
    -0.06
    æľªå®ĮæĪIJ
    -0.06
    对çħ§
    -0.06
    iring
    -0.06
    åĶ¯æľī
    -0.06
    æĭ¼
    -0.06
    POSITIVE LOGITS
    ampa
    0.10
    eeper
    0.08
    ests
    0.08
    .ready
    0.07
    ahead
    0.07
    微信平åı°
    0.07
    lobs
    0.07
    Reach
    0.07
     beforehand
    0.07
    oppins
    0.07
    Activations Density 0.050%

    No Known Activations