© 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. 17102
    Prev
    Next
    INDEX
    Explanations

    you see her smile

    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
    ↵
    -0.05
    emer
    -0.05
    çľĭä¸į
    -0.05
    "
    -0.05
    åºĶåıĺ
    -0.05
    èĩŃ
    -0.04
     upstream
    -0.04
    Cl
    -0.04
     horizontal
    -0.04
     accord
    -0.04
    POSITIVE LOGITS
     célé
    0.07
    éĥİ
    0.07
     fré
    0.06
    åįķ人
    0.06
     Kab
    0.06
    ห
    0.06
    cel
    0.06
     :*
    0.06
    kof
    0.06
     Pair
    0.06
    Activations Density 0.060%

    No Known Activations