© 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. 56954
    Prev
    Next
    INDEX
    Explanations

    mathematical mappings and code syntax

    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
    avat
    -0.08
    ancam
    -0.07
    éĩĬ
    -0.06
     nik
    -0.06
    NCY
    -0.06
    临éŨ
    -0.06
    ucha
    -0.06
    .mock
    -0.06
    ncmp
    -0.06
    _MALLOC
    -0.06
    POSITIVE LOGITS
    /from
    0.08
    erer
    0.07
    urus
    0.07
    ož
    0.07
     Vox
    0.07
    ÑĪенко
    0.07
    æĸ¹èĪŁ
    0.07
    举
    0.07
    ellido
    0.07
    ¦
    0.07
    Activations Density 0.005%

    No Known Activations