© 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. 19922
    Prev
    Next
    INDEX
    Explanations

    lie ahead or lurking

    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
    æĦģ
    -0.05
    اÙĦÙĩ
    -0.05
    lave
    -0.05
    ra
    -0.05
    ÙĬÙĭا
    -0.05
    /run
    -0.05
    ÑģоÑĤ
    -0.04
    hoa
    -0.04
    úng
    -0.04
    cule
    -0.04
    POSITIVE LOGITS
    yped
    0.07
    ëĭĪ
    0.06
    amani
    0.06
    ¾
    0.06
    finish
    0.06
    çıį
    0.06
    å¤ĸçĶ¨
    0.06
    ylene
    0.06
    endez
    0.06
    หมาย
    0.06
    Activations Density 0.008%

    No Known Activations