© 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. 23727
    Prev
    Next
    INDEX
    Explanations

    high low properties

    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
    éįĬ
    -0.09
    (rawValue
    -0.08
    ä¸īåı·
    -0.08
    天æŶ
    -0.07
    å°ļ
    -0.07
    è¿ĺå¤Ħäºİ
    -0.07
    å°ı家
    -0.07
    assi
    -0.07
    ])[
    -0.07
     Fancy
    -0.07
    POSITIVE LOGITS
     predictable
    0.09
    çŃīä¸Ģç³»åĪĹ
    0.07
     predict
    0.07
    åIJĦ级
    0.07
     conserv
    0.07
    çŃīè¡Į为
    0.07
    çŃīçݰ象
    0.07
     countless
    0.07
    伶
    0.06
     properties
    0.06
    Activations Density 0.014%

    No Known Activations