© 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. 21409
    Prev
    Next
    INDEX
    Explanations

    language isolate

    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
    -0.06
     bin
    -0.05
     L
    -0.05
    æĸĩ
    -0.05
     Mach
    -0.05
     [
    -0.05
     nos
    -0.05
     bac
    -0.04
     Latin
    -0.04
     gran
    -0.04
    POSITIVE LOGITS
    áng
    0.07
    onderen
    0.07
    íĻĺ
    0.07
    /gallery
    0.07
    kring
    0.07
    kert
    0.07
    amientos
    0.06
    rak
    0.06
    ként
    0.06
     Emergen
    0.06
    Activations Density 0.003%

    No Known Activations