© 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. 30081
    Prev
    Next
    INDEX
    Explanations

    sample extraction and preparation

    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
     rand
    -0.07
    项
    -0.07
    jit
    -0.06
     term
    -0.06
    å½ĵåħ¶
    -0.06
    çľ¼åħī
    -0.06
    èī¯åĵģ
    -0.06
    覧
    -0.06
     lok
    -0.06
     graceful
    -0.06
    POSITIVE LOGITS
    é¢Ħå¤ĦçIJĨ
    0.12
     preprocessing
    0.09
    åĬłåĪĨ
    0.09
    ê´Ħ
    0.08
    ipan
    0.08
     preprocess
    0.08
    è¿ĩå¤ľ
    0.08
    å¼ĢæĶ¾å¼ı
    0.08
     capturing
    0.08
     precon
    0.08
    Activations Density 0.140%

    No Known Activations