© 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. 19566
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    anium
    -0.08
    žd
    -0.08
    解éĩĬéģĵ
    -0.08
    ä¸Ĭè·¯
    -0.08
    ä¸ĬæīĢ
    -0.07
    rap
    -0.07
    çĶµèĦijçīĪ
    -0.07
     uptime
    -0.07
    paro
    -0.07
    继
    -0.07
    POSITIVE LOGITS
    ought
    0.08
    /+
    0.08
    ãĥ«ãĥķ
    0.07
    акÑĤеÑĢ
    0.07
    onan
    0.07
    _SCROLL
    0.07
    èĮģ
    0.07
    veis
    0.07
    bound
    0.07
    黯
    0.07
    Activations Density 0.071%

    No Known Activations