© 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. 20761
    Prev
    Next
    INDEX
    Explanations

    fill in

    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
     richies
    -0.08
    onor
    -0.07
    æĬĺä¸į
    -0.07
     unsuccessfully
    -0.07
    家åĸ»
    -0.07
    žen
    -0.07
     prévo
    -0.07
    iscrim
    -0.07
    é¾Ħ
    -0.07
    åĺĮåij¤
    -0.07
    POSITIVE LOGITS
    olat
    0.05
    olak
    0.05
    ?
    0.05
    “
    0.05
    éķľ
    0.05
    ä¾ĭ
    0.05
    åģĩ
    0.04
    å¼ı
    0.04
    äºĭ
    0.04
    .
    0.04
    Activations Density 0.003%

    No Known Activations