© 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. 9496
    Prev
    Next
    INDEX
    Explanations

    organization and structure

    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
    ÙĦات
    -0.09
    _extra
    -0.08
    hofer
    -0.08
    ipun
    -0.08
    ãĥªãĥĨãĤ£
    -0.08
    缸åºĶ
    -0.08
    è½°è½°
    -0.08
    avance
    -0.07
    缸åºĶçļĦ
    -0.07
    sula
    -0.07
    POSITIVE LOGITS
    reb
    0.07
     overarching
    0.06
     soul
    0.06
     broadly
    0.06
    åį³å¢¨
    0.05
    ail
    0.05
    æĢ»åı°
    0.05
    è¡Įä¹ĭ
    0.05
     Gr
    0.05
     Elo
    0.05
    Activations Density 0.001%

    No Known Activations