© 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. 30445
    Prev
    Next
    INDEX
    Explanations

    lambda functions in code

    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
    adol
    -0.07
    rim
    -0.07
    ners
    -0.06
    elaar
    -0.06
    pel
    -0.06
    éĢĤå½ĵåľ°
    -0.06
    å¼Ģå±ķçļĦ
    -0.06
    ern
    -0.06
    rop
    -0.06
    对äºİæĪij们
    -0.06
    POSITIVE LOGITS
    žas
    0.07
    ulette
    0.07
    ä¸įæİ¥åıĹ
    0.07
    unused
    0.07
    uilder
    0.07
    owering
    0.07
     _:
    0.07
    alités
    0.07
    ä¸ľè¥¿
    0.07
     rara
    0.06
    Activations Density 0.036%

    No Known Activations