© 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. 19871
    Prev
    Next
    INDEX
    Explanations

    punctuation and code delimiters

    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
     Admin
    -0.05
     row
    -0.05
    ↵
    -0.04
     Hel
    -0.04
    ç»
    -0.04
     fl
    -0.04
     underline
    -0.04
     password
    -0.04
    æı
    -0.04
    fh
    -0.04
    POSITIVE LOGITS
    å¤ļå¾Ĺ
    0.07
    Ñħло
    0.07
    ecto
    0.07
    ulte
    0.07
    ipo
    0.07
    麻麻
    0.07
     klo
    0.07
    olson
    0.07
    unya
    0.07
    jÄĻ
    0.07
    Activations Density 0.012%

    No Known Activations