© 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. 19394
    Prev
    Next
    INDEX
    Explanations

    dates and durations

    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
     altrett
    -0.06
    éĸ±
    -0.06
    avian
    -0.06
    ity
    -0.05
    ç«ĭ
    -0.05
     mani
    -0.05
    Origin
    -0.05
    çļĦäººæł¼
    -0.05
    ingo
    -0.05
    ourney
    -0.05
    POSITIVE LOGITS
    å°½ãģı
    0.06
    软
    0.06
    ä¾ł
    0.06
    ×ĺ×Ķ
    0.06
    /dev
    0.06
    eligible
    0.06
     diagnost
    0.06
    æľ«
    0.05
     полно
    0.05
    Ùħار
    0.05
    Activations Density 0.032%

    No Known Activations