© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18513
    Prev
    Next
    INDEX
    Explanations

    numbers and specific text types

    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
    opt
    -0.06
     bon
    -0.05
    رائ
    -0.05
    wal
    -0.05
     variant
    -0.05
     subclass
    -0.05
    heets
    -0.05
    etail
    -0.05
    hou
    -0.05
    à¹Ģà¸ķ
    -0.05
    POSITIVE LOGITS
    èį¨
    0.07
    {@
    0.06
    üz
    0.06
    frequ
    0.06
    zig
    0.06
    äºİä»Ĭå¹´
    0.06
    chema
    0.06
    orra
    0.06
    vento
    0.06
    cadena
    0.06
    Activations Density 0.001%

    No Known Activations