© 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. 16157
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    _POLICY
    -0.07
    ä¹ĭä¸Ģæĺ¯
    -0.06
    ideshow
    -0.06
    åĴĮä¿¡æģ¯åĮĸ
    -0.06
    èĴ¸èĴ¸æĹ¥ä¸Ĭ
    -0.06
    èĹ»
    -0.06
    å²Ķ
    -0.06
     uniformly
    -0.06
     rowspan
    -0.06
    åŃ£
    -0.06
    POSITIVE LOGITS
    atian
    0.08
    ä½ĵèĤ²è¿IJåĬ¨
    0.08
    chs
    0.07
    ATEST
    0.07
    оÑĤе
    0.07
    ãĥĦ
    0.07
    è§ģ人
    0.07
    alth
    0.07
    å°Ĭ严
    0.07
    ivr
    0.07
    Activations Density 0.002%

    No Known Activations