© 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. 12577
    Prev
    Next
    INDEX
    Explanations

    array, slice, frames, column, generate

    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
     cann
    -0.08
     pent
    -0.07
    åĩºæīĭ
    -0.07
    arre
    -0.06
     prest
    -0.06
    ä¸īæĹł
    -0.06
     parents
    -0.06
    çĪ¶æ¯į
    -0.06
    _globals
    -0.06
     Basic
    -0.06
    POSITIVE LOGITS
    (vertical
    0.09
    åŀĤ缴
    0.08
    ForEach
    0.08
    ayani
    0.08
    opyright
    0.08
    -column
    0.08
    ä¹ħä¹ĭ
    0.08
    ä¸Ĭ好
    0.08
    æķĻèĤ²åѦéĻ¢
    0.07
    (Column
    0.07
    Activations Density 0.033%

    No Known Activations