© 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. 19908
    Prev
    Next
    INDEX
    Explanations

    lightweight structure

    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
    ittee
    -0.07
    ationen
    -0.07
    èIJ½èIJ½
    -0.07
    åŁĭåľ¨
    -0.06
    berra
    -0.06
    thinkable
    -0.06
    fru
    -0.06
    ServiceImpl
    -0.06
    gings
    -0.06
    ,DB
    -0.06
    POSITIVE LOGITS
    èĮµ
    0.06
    é£İæļ´
    0.05
     Verm
    0.05
     atmosphere
    0.05
    èĩªç«ĭ
    0.05
    ins
    0.05
    quake
    0.05
    volle
    0.05
    y
    0.05
    ówczas
    0.05
    Activations Density 0.008%

    No Known Activations