© 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. 20834
    Prev
    Next
    INDEX
    Explanations

    fluent english speaker

    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
    kea
    -0.06
     depths
    -0.06
    utus
    -0.06
    eut
    -0.06
    infos
    -0.06
    çł´æµª
    -0.06
    試ç®Ĺ
    -0.05
    tide
    -0.05
    kut
    -0.05
    éĿłèijĹ
    -0.05
    POSITIVE LOGITS
     maneuver
    0.07
     Mane
    0.06
    åįķä¸Ģ
    0.05
    shed
    0.05
    å¼Ĥ
    0.05
    å¤ĸæĿ¥
    0.05
    uy
    0.05
     alle
    0.05
    cast
    0.05
    eman
    0.05
    Activations Density 0.007%

    No Known Activations