© 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. 58182
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and syntax

    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
    çĽĺé¾Ļ
    -0.07
     minus
    -0.07
    gregate
    -0.07
    çŁ¥éģĵä»ĸ
    -0.07
    gnu
    -0.06
    åIJİéĢĢ
    -0.06
    æĸ°ä½İ
    -0.06
    çĩİ
    -0.06
    adiens
    -0.06
    linger
    -0.06
    POSITIVE LOGITS
    ulo
    0.09
    ULO
    0.08
    pris
    0.07
    åħ³ç³»
    0.07
    ulas
    0.06
    uld
    0.06
    uml
    0.06
    OLO
    0.06
    åŀĭ人æīį
    0.06
    ardin
    0.06
    Activations Density 0.001%

    No Known Activations