© 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. 20368
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and sorting

    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
    inking
    -0.09
    _FB
    -0.08
    oksi
    -0.08
    大æīĵæĬĺæī£
    -0.07
    éĢĬ
    -0.07
    #$
    -0.07
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    -0.07
    å¼ģ
    -0.07
    éģľ
    -0.07
    eman
    -0.07
    POSITIVE LOGITS
    asca
    0.07
    åıĪå¦Ĥ
    0.07
    eel
    0.06
    cet
    0.06
    ule
    0.06
    2
    0.06
    ä¾ĭ
    0.06
      ↵
    0.06
    Âł
    0.06
    çļĦ女çĶŁ
    0.05
    Activations Density 0.002%

    No Known Activations