© 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. 20950
    Prev
    Next
    INDEX
    Explanations

    renovation and remodel

    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
    bre
    -0.07
    chia
    -0.06
     disposit
    -0.06
    äºİæѤ
    -0.06
    .pm
    -0.06
    ãĤĴå®Ī
    -0.06
    aista
    -0.06
     geograf
    -0.06
    etros
    -0.06
    .fre
    -0.06
    POSITIVE LOGITS
     transforming
    0.06
    ild
    0.06
    ä¸įè°ĥ
    0.06
    ä¸Ńè·¯
    0.05
     transformation
    0.05
     transforms
    0.05
    Transform
    0.05
     undertaken
    0.05
    å±Ģéĥ¨
    0.05
    æĶ¹éĢł
    0.05
    Activations Density 0.046%

    No Known Activations