© 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. 38726
    Prev
    Next
    INDEX
    Explanations

    numbers followed by nouns

    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
     demais
    -0.08
    èĭ¥å¹²
    -0.08
     certain
    -0.07
    åħ·ä½ĵåĪĨæŀIJ
    -0.07
     diverses
    -0.07
     various
    -0.07
     stuff
    -0.07
     another
    -0.07
     enough
    -0.07
    oes
    -0.07
    POSITIVE LOGITS
    æĪĸéĥ¨åĪĨ
    0.11
     sides
    0.09
     تÙĤرÙĬب
    0.08
    igus
    0.08
    инÑĭ
    0.08
     ש׾
    0.07
    à¹Ģลย
    0.07
    verständlich
    0.07
    -sided
    0.07
    essian
    0.07
    Activations Density 0.011%

    No Known Activations