© 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. 30614
    Prev
    Next
    INDEX
    Explanations

    voltage-controlled circuits

    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
    OrUpdate
    -0.07
    ergus
    -0.07
    alus
    -0.06
    æķ°éĩı为
    -0.06
    ar
    -0.06
    er
    -0.06
    à¹Ī
    -0.06
    emann
    -0.06
    ä¼ļéĢīæĭ©
    -0.06
    æ´Ľä¼Ĭ
    -0.06
    POSITIVE LOGITS
    /current
    0.11
    ierz
    0.10
     забÑĥ
    0.09
    IRTUAL
    0.08
    iclet
    0.08
    iers
    0.08
    à¤Ĥतर
    0.08
    antie
    0.08
    icación
    0.08
    ØŃÙĪ
    0.08
    Activations Density 0.012%

    No Known Activations