© 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. 2128
    Prev
    Next
    INDEX
    Explanations

    Esperanto month names

    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
    inkel
    -0.08
    yno
    -0.08
    æŀĹä¸ļå±Ģ
    -0.08
    渺
    -0.08
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.07
    неÑĤа
    -0.07
    æı½
    -0.07
    ariat
    -0.07
    ä¸įæĺ¯åIJĹ
    -0.07
    haw
    -0.07
    POSITIVE LOGITS
    åįļæĸĩ
    0.07
    åħ±åIJĮ
    0.07
    å¤ļåĬł
    0.07
    åĨįåĬł
    0.07
    äºĮ代
    0.06
    å¦ĤæѤ
    0.06
    ult
    0.06
    Web
    0.06
    agu
    0.06
    çĶŁ
    0.06
    Activations Density 0.021%

    No Known Activations