© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22212
    Prev
    Next
    INDEX
    Explanations

    ethyl derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¸
    -0.05
    em
    -0.05
    les
    -0.05
    çļĦæĺ¯
    -0.05
    de
    -0.05
    cing
    -0.05
     extent
    -0.05
    gel
    -0.05
    uction
    -0.05
     '
    -0.05
    POSITIVE LOGITS
     newcom
    0.07
    kerne
    0.07
    tvr
    0.07
    дÑĬÑĢжа
    0.07
    utri
    0.07
    ormsg
    0.07
    æĸ°æ¦Ĥ念
    0.07
     manch
    0.07
     Kabar
    0.07
    -la
    0.07
    Activations Density 0.015%

    No Known Activations