© 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. 21252
    Prev
    Next
    INDEX
    Explanations

    naming or being named

    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
     Lees
    -0.07
    rotch
    -0.07
    зна
    -0.06
    jata
    -0.06
    jal
    -0.06
    åĸľæ¬¢ä½ł
    -0.06
    æѤæĸĩ
    -0.06
    lush
    -0.06
    çĹħ
    -0.06
    ussen
    -0.06
    POSITIVE LOGITS
    å°±åı«
    0.16
    åij½åIJį为
    0.15
    çļĦåIJį称
    0.14
     naming
    0.13
    åıĸåIJį
    0.13
     named
    0.13
    å¾ĹåIJį
    0.12
    ç§°ä½ľ
    0.12
    æĶ¹åIJį
    0.12
    åij½åIJį
    0.12
    Activations Density 0.321%

    No Known Activations