© 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. 32721
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    èı©æıIJ
    -0.07
    楷
    -0.07
    yno
    -0.06
     middel
    -0.06
    娥
    -0.06
    pped
    -0.06
    å®Ī
    -0.06
    éļ¶
    -0.06
    iffer
    -0.06
    çķı
    -0.06
    POSITIVE LOGITS
    -END
    0.09
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.08
    ç©«
    0.08
    *”,
    0.07
    以ä¸Ĭæĺ¯
    0.07
    -Sah
    0.07
    adak
    0.07
    eload
    0.07
     ãĤ¹ãĥĿãĥ³
    0.07
    FRING
    0.07
    Activations Density 0.434%

    No Known Activations