© 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. 17304
    Prev
    Next
    INDEX
    Explanations

    hiring people

    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
    åĦĢ
    -0.06
     metr
    -0.06
     bel
    -0.06
    zem
    -0.06
    еÑģе
    -0.06
    enties
    -0.06
    맹
    -0.06
    nitz
    -0.06
    chluss
    -0.06
    ikker
    -0.06
    POSITIVE LOGITS
     locked
    0.06
    éĶģ
    0.05
    ниÑĨа
    0.05
    å²
    0.05
    ãĤĨ
    0.05
     population
    0.05
     lock
    0.05
    portion
    0.05
    人æīį
    0.05
    éĿĴ
    0.05
    Activations Density 0.018%

    No Known Activations