© 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. 32318
    Prev
    Next
    INDEX
    Explanations

    programming language code

    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
    åıijèµ·
    -0.06
    åħ·
    -0.06
    æħ·æħ¨
    -0.06
    alam
    -0.06
    lobals
    -0.06
    à§į
    -0.06
    apol
    -0.06
    è¯ļå¿ĥ
    -0.06
    é¡į
    -0.06
     Labs
    -0.06
    POSITIVE LOGITS
    åľºä¸ĬçļĦ
    0.08
    çĦ¶åIJİåıĪ
    0.08
    ady
    0.08
     deles
    0.07
    ulti
    0.07
     bep
    0.07
    èĢĮè¿Ļ
    0.07
    éĨ¤
    0.07
    implements
    0.07
    utting
    0.07
    Activations Density 0.083%

    No Known Activations