© 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. 17954
    Prev
    Next
    INDEX
    Explanations

    names followed by common closings

    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
    ustru
    -0.07
    yai
    -0.07
     ÑĥÑģÑĤановленном
    -0.07
    szyscy
    -0.06
    Stunden
    -0.06
    ancar
    -0.06
    égr
    -0.06
     **âĸł
    -0.06
    ystore
    -0.06
    uhe
    -0.06
    POSITIVE LOGITS
    ael
    0.05
    atz
    0.05
     =
    0.05
    +
    0.05
     cust
    0.05
    ued
    0.05
    kunde
    0.05
     cons
    0.05
    -
    0.05
     *
    0.05
    Activations Density 0.062%

    No Known Activations