© 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. 50333
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    碧
    -0.07
    çijŀå®ī
    -0.07
    äºĨä¸ĢåĪĩ
    -0.07
    outu
    -0.07
    ืà¸Ķ
    -0.06
    åŁ
    -0.06
    å°½
    -0.06
    æĺĤ
    -0.06
    è¾ī
    -0.06
    åĬ£
    -0.06
    POSITIVE LOGITS
    以èĩ³
    0.08
    è¡
    0.07
    个åŃĹ
    0.07
     Retrieves
    0.07
    laub
    0.07
    иÑģÑĤо
    0.07
    ocale
    0.07
    orgen
    0.07
    oš
    0.07
     retrieval
    0.07
    Activations Density 0.000%

    No Known Activations