© 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. 20839
    Prev
    Next
    INDEX
    Explanations

    requesting or seeking something

    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
    人马
    -0.06
    è¾Ħ
    -0.06
    Ñģай
    -0.06
    Sy
    -0.06
    uely
    -0.06
     sy
    -0.06
     Sy
    -0.06
    andes
    -0.05
     Synd
    -0.05
     constate
    -0.05
    POSITIVE LOGITS
    è¯Ŀ
    0.07
    uggle
    0.06
    èµĦ
    0.06
    dauer
    0.05
    å°ıçĻ½
    0.05
    dik
    0.05
    idden
    0.05
     postul
    0.05
    æĪIJçļĦ
    0.05
    æĹłæŃ¢å¢ĥ
    0.05
    Activations Density 0.009%

    No Known Activations