© 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. 10132
    Prev
    Next
    INDEX
    Explanations

    file operations or code structures

    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
    erb
    -0.08
    åIJ¸çº³
    -0.06
    ogl
    -0.06
     à¸ļรร
    -0.06
    atte
    -0.06
     âĤ¬,
    -0.06
    姥çĪ·
    -0.06
     sh
    -0.05
    _COMPONENT
    -0.05
    ula
    -0.05
    POSITIVE LOGITS
    ephy
    0.08
    å°±æĺ¯è¿Ļä¹Ī
    0.08
    igon
    0.08
    ockey
    0.08
    leti
    0.08
    laughter
    0.08
    лдÑĭ
    0.08
    aruh
    0.08
    MBER
    0.08
    <strong
    0.08
    Activations Density 0.075%

    No Known Activations