© 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. 45310
    Prev
    Next
    INDEX
    Explanations

    [@B<number>] citations

    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
    ilter
    -0.08
    eldom
    -0.08
    aktu
    -0.08
    erre
    -0.08
    å·´æĭī
    -0.08
    åħ³äºİæĪij们
    -0.07
    ilus
    -0.07
     наÑĢа
    -0.07
    à¹Īà¸Ńà¸Ļ
    -0.07
    pton
    -0.07
    POSITIVE LOGITS
    دÙĬ
    0.07
    i
    0.06
    DK
    0.06
    ovas
    0.06
    追
    0.06
     post
    0.06
     chem
    0.06
     convincing
    0.06
    less
    0.06
    Credit
    0.06
    Activations Density 0.002%

    No Known Activations