© 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. 21201
    Prev
    Next
    INDEX
    Explanations

    mutations=

    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
     hovering
    -0.05
    ennifer
    -0.05
    ful
    -0.05
     alber
    -0.05
     hover
    -0.05
     lia
    -0.05
    ativity
    -0.05
    é¡¿äºĨ
    -0.05
    issor
    -0.05
    ä»İ没
    -0.05
    POSITIVE LOGITS
    ECT
    0.07
    éģĵéķ¿
    0.06
    اÙĦب
    0.06
    å¤§åĽ¾
    0.06
    Beh
    0.06
    éĽĨä¸ŃçļĦ
    0.06
     Greene
    0.05
    פ×ķר
    0.05
    äh
    0.05
     congest
    0.05
    Activations Density 0.023%

    No Known Activations