© 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. 3227
    Prev
    Next
    INDEX
    Explanations

    colon, followed by EDIT

    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
    quire
    -0.07
    acy
    -0.07
    fé
    -0.06
    -time
    -0.06
    ooth
    -0.06
     counters
    -0.06
    çĥĪ
    -0.06
    ieves
    -0.06
    spark
    -0.06
    inum
    -0.06
    POSITIVE LOGITS
    кÑĸн
    0.09
    -addons
    0.08
    è¡¥åħħ
    0.08
    *@
    0.07
    hirt
    0.07
    åıĪ大
    0.07
    è£ľåħħ
    0.07
    #"
    0.07
    åľ¨ä¸İ
    0.07
     bı
    0.07
    Activations Density 0.045%

    No Known Activations