© 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. 21561
    Prev
    Next
    INDEX
    Explanations

    `parallel` `MODULE` `namespace` `Find`

    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
    (
    -0.06
    ke
    -0.06
    i
    -0.06
     implanta
    -0.06
    åģļ好
    -0.06
    ir
    -0.05
    -
    -0.05
    uru
    -0.05
    å±ħçĦ¶
    -0.05
    éĿĴåħī
    -0.05
    POSITIVE LOGITS
    éĢļè¿ĩ以ä¸Ĭ
    0.11
    以ä¸ĬåĨħ容
    0.10
    以ä¸Ĭå°±æĺ¯
    0.10
    å°±ç»ĵæĿŁäºĨ
    0.09
    èĩ³æѤ
    0.08
    ãģĵãģĵãģ¾ãģ§
    0.08
    BUTTON
    0.08
    wai
    0.08
    èŀŁ
    0.08
    æľ«
    0.08
    Activations Density 0.108%

    No Known Activations