© 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. 25627
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with 'l'

    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
    æģĭ
    -0.07
    ipel
    -0.07
    hluk
    -0.07
    ipmap
    -0.07
    æĹłå¿ĥ
    -0.07
    agu
    -0.06
    zze
    -0.06
     `,
    -0.06
    以åıĬä¸ĢäºĽ
    -0.06
    áh
    -0.06
    POSITIVE LOGITS
    byg
    0.07
     подÑĬ
    0.06
    )['
    0.06
    alais
    0.06
    )["
    0.06
    åĪ°ä½į
    0.06
    è§ģä»ĸ
    0.06
    溫æ³ī
    0.06
    ekali
    0.06
    evil
    0.06
    Activations Density 0.001%

    No Known Activations