© 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. 28447
    Prev
    Next
    INDEX
    Explanations

    one-dimensional

    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
    rame
    -0.08
    Partial
    -0.07
    ãĥ³ãĥĹ
    -0.07
    ölf
    -0.07
    å¥ĸçļĦ
    -0.07
    æł¼çļĦ
    -0.07
     Moff
    -0.07
    ieves
    -0.07
    æĭľæīĺ
    -0.07
    iffin
    -0.06
    POSITIVE LOGITS
    /single
    0.10
    åįķä¸Ģ
    0.10
    åįķè°ĥ
    0.10
    (single
    0.10
    åįķ
    0.10
    çĭ¬
    0.10
    alone
    0.09
    åįķä¸ĢçļĦ
    0.09
    åįķ项
    0.09
    éĵ¾
    0.09
    Activations Density 0.079%

    No Known Activations