© 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. 21517
    Prev
    Next
    INDEX
    Explanations

    boolean questions

    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
    GOR
    -0.07
    ligen
    -0.06
    ов
    -0.06
    ноÑĢа
    -0.06
    itals
    -0.06
    uken
    -0.06
    aglio
    -0.06
    AYA
    -0.06
    æŃĩå°Ķ
    -0.06
    θα
    -0.06
    POSITIVE LOGITS
    hem
    0.05
     isol
    0.05
     agr
    0.05
    eman
    0.05
    bran
    0.05
    ...
    0.05
    e
    0.05
    ipur
    0.05
    <span
    0.05
    üt
    0.05
    Activations Density 0.003%

    No Known Activations