© 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. 27944
    Prev
    Next
    INDEX
    Explanations

    sentence start

    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
    andu
    -0.08
    ungan
    -0.08
     dite
    -0.08
    axter
    -0.08
    üter
    -0.07
    ommer
    -0.07
     Aner
    -0.07
    åį´ä¸įèĥ½
    -0.07
    å§ĭç»Ī以
    -0.07
    оÑĢÑĥ
    -0.07
    POSITIVE LOGITS
    éĹĩ
    0.07
    izr
    0.07
     impro
    0.06
    siz
    0.06
    ramid
    0.06
    rise
    0.06
     nid
    0.06
    èĺĭ
    0.06
    ie
    0.06
    ÙĦÙģت
    0.06
    Activations Density 0.015%

    No Known Activations