© 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. 20794
    Prev
    Next
    INDEX
    Explanations

    testing code snippets

    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
    ü
    -0.06
     lowest
    -0.05
    ore
    -0.05
    èĭ¦
    -0.05
     populated
    -0.05
    ↵
    -0.05
    ×ķ×Ĺ
    -0.05
    ’
    -0.04
     (
    -0.04
    ie
    -0.04
    POSITIVE LOGITS
    hnya
    0.07
     hạn
    0.07
    isar
    0.07
    ynu
    0.07
    ãģĻãģĻ
    0.07
    ÑĢал
    0.07
     besonder
    0.07
     kulinar
    0.07
    hya
    0.07
    rases
    0.06
    Activations Density 0.321%

    No Known Activations