© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    the word "acting" or words ending in "Dr" in technical or formal documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    âĢ¦..
    -0.08
     utilizing
    -0.08
     ****
    -0.08
    ****
    -0.07
     +/-
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
     categorized
    -0.07
    å½ĵåģļ
    -0.07
    -0.07
     fucked
    -0.07
    POSITIVE LOGITS
    âĢij
    0.09
     hoá
    0.08
    æľ¬å°±
    0.08
     neighbours
    0.07
     Initialise
    0.07
     colour
    0.07
     untouched
    0.07
     tiny
    0.07
    éļĻ
    0.07
     пÑĢиÑijм
    0.07
    Activations Density 0.000%

    No Known Activations