© 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. 18254
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sqrt

    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
    ience
    -0.06
    ä»İåīį
    -0.06
    ↵↵
    -0.06
    lene
    -0.06
    onacci
    -0.06
    å°ıè§Ħ模
    -0.05
     SGK
    -0.05
    —
    -0.05
     beyond
    -0.05
    åľ¨è®¾è®¡
    -0.05
    POSITIVE LOGITS
     fras
    0.09
    icc
    0.08
    zyn
    0.08
    ycz
    0.08
    ัว
    0.08
    ujur
    0.08
    ict
    0.07
    åķĬåķĬ
    0.07
    ิริ
    0.07
    å·²èµŀè¿ĩ
    0.07
    Activations Density 0.004%

    No Known Activations