© 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. 19956
    Prev
    Next
    INDEX
    Explanations

    request controller

    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
    iros
    -0.07
    umas
    -0.07
    adamente
    -0.07
    åıĬåij¨è¾¹
    -0.07
    iÄį
    -0.06
    ilus
    -0.06
    iec
    -0.06
    ated
    -0.06
    ous
    -0.06
    ota
    -0.06
    POSITIVE LOGITS
    ÏĦαι
    0.11
    -vous
    0.09
    /releases
    0.09
    /is
    0.09
    ÙĪÙĨ
    0.09
    ÛķÙĪÛķ
    0.09
    ÑģÑı
    0.09
    nt
    0.09
    /rem
    0.08
    ÑĤÑģÑı
    0.08
    Activations Density 0.073%

    No Known Activations