© 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. 48829
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by letters

    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
    ÏĦηÏĥη
    -0.08
    amework
    -0.08
    beiter
    -0.08
    าà¸Ļุ
    -0.08
    ׼×ķף
    -0.08
    धान
    -0.08
     stat
    -0.07
    emeld
    -0.07
    egel
    -0.07
    eld
    -0.07
    POSITIVE LOGITS
    phis
    0.07
     alike
    0.06
     Yıld
    0.06
    绪
    0.06
     respectively
    0.06
    ç»ĦæĪIJéĥ¨åĪĨ
    0.06
     Alfon
    0.06
    uala
    0.06
    atele
    0.06
    airo
    0.06
    Activations Density 0.091%

    No Known Activations