© 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. 17715
    Prev
    Next
    INDEX
    Explanations

    ","chr","UK","SCC","WN","Five"

    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
    åĽ½åľŁ
    -0.06
    aum
    -0.06
     whom
    -0.05
    ä»Ļ
    -0.05
    inth
    -0.05
     Hutch
    -0.05
     коÑĤоÑĢÑĭм
    -0.05
    inata
    -0.05
     chay
    -0.05
    _H
    -0.05
    POSITIVE LOGITS
    æĵį
    0.06
    UNE
    0.06
    çŀ
    0.05
    work
    0.05
    kins
    0.05
    icie
    0.05
    æĪijçļĦå¿ĥæĥħ
    0.05
    undene
    0.05
    sted
    0.05
    acter
    0.05
    Activations Density 0.003%

    No Known Activations