© 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. 14267
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and notation

    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
    åı¸ç©º
    -0.07
    سÙĬر
    -0.06
    usize
    -0.06
    ToObject
    -0.06
     deb
    -0.06
    allen
    -0.06
    alen
    -0.06
    è¿«ä¸įåıĬå¾ħåľ°
    -0.06
    [_
    -0.06
    ara
    -0.06
    POSITIVE LOGITS
     itself
    0.08
    æĿĢæīĭ
    0.08
    epad
    0.08
    æľ¬èº«
    0.08
    èĩªå¸¦
    0.08
    å·²æľīçļĦ
    0.08
    dut
    0.07
    æĿĢ
    0.07
     existing
    0.07
    æĶ¾çŁ¢
    0.07
    Activations Density 0.005%

    No Known Activations