© 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. 17167
    Prev
    Next
    INDEX
    Explanations

    new materials

    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
    emiz
    -0.06
    æĹłåıį
    -0.05
    ç»Ī
    -0.05
    ç¼ĸ
    -0.05
    Looper
    -0.05
    äºĨå¤ļå°ij
    -0.05
     spokeswoman
    -0.05
     scav
    -0.05
    们
    -0.04
     pér
    -0.04
    POSITIVE LOGITS
    rod
    0.06
    lace
    0.06
    ża
    0.06
    æŦ
    0.06
    edor
    0.06
    åIJģ
    0.06
    osphere
    0.06
    ÑģиÑĤ
    0.06
    覺
    0.05
     Ñģебе
    0.05
    Activations Density 0.001%

    No Known Activations