© 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. 50737
    Prev
    Next
    INDEX
    Explanations

    prize

    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
    ouro
    -0.08
    就说
    -0.07
    ri
    -0.07
    ESC
    -0.07
    צ×Ķ
    -0.07
    lod
    -0.06
    ä¸įæľį
    -0.06
     propTypes
    -0.06
    ä¸įåıĬå¾ħ
    -0.06
    CLA
    -0.06
    POSITIVE LOGITS
     Varese
    0.07
    insic
    0.07
    jee
    0.07
    _MUL
    0.07
    éĿ¡
    0.07
    å¿ħåħĪ
    0.06
    à¸Ħà¸Ļหà¸Ļึà¹Īà¸ĩ
    0.06
    ocop
    0.06
    _sparse
    0.06
    atto
    0.06
    Activations Density 0.001%

    No Known Activations