© 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. 30724
    Prev
    Next
    INDEX
    Explanations

    thylakoids and chloroplasts

    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
    клон
    -0.08
    optgroup
    -0.07
    truncate
    -0.07
     Ñħло
    -0.07
    лоÑĤ
    -0.07
    ippet
    -0.07
    è´Łéĩį
    -0.07
    ebro
    -0.07
    容éĩıçļĦ
    -0.07
    menge
    -0.06
    POSITIVE LOGITS
    Parte
    0.08
     parte
    0.08
    ewater
    0.07
     ctype
    0.07
    ĶĦ
    0.07
    gulan
    0.07
    æĮĩå®ļåľ°çĤ¹
    0.07
    rze
    0.07
    agged
    0.07
    âĻª
    0.07
    Activations Density 0.001%

    No Known Activations