© 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. 41186
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    agni
    -0.08
    elts
    -0.07
    echa
    -0.06
    acap
    -0.06
    adis
    -0.06
    å®Ŀ
    -0.06
     clues
    -0.06
    åIJijä¸ĭ
    -0.06
    çģ«çº¿
    -0.06
     clue
    -0.06
    POSITIVE LOGITS
    èIJ¦
    0.08
    arrer
    0.08
    笤
    0.07
    æľīçļĦæŶåĢĻ
    0.07
    dragon
    0.07
    #ac
    0.07
    é¨
    0.07
    оÑģÑĥ
    0.07
    wenc
    0.07
    lipse
    0.07
    Activations Density 0.000%

    No Known Activations