© 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. 8413
    Prev
    Next
    INDEX
    Explanations

    first one

    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
    ipel
    -0.09
    inen
    -0.07
     rued
    -0.07
    zel
    -0.07
    çľĭåĪ°è¿Ļ个
    -0.07
    ((*
    -0.07
    opard
    -0.07
    åĨ
    -0.07
    ospel
    -0.06
    _DIP
    -0.06
    POSITIVE LOGITS
    onna
    0.07
    usra
    0.07
    ä¹ĭæīĢ以
    0.07
    spur
    0.07
    ä¸Ģèµ·åŃ¦ä¹ł
    0.06
    #ac
    0.06
     Option
    0.06
    owan
    0.06
     باÙĦÙĨسبة
    0.06
    IGE
    0.06
    Activations Density 0.001%

    No Known Activations