© 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. 21627
    Prev
    Next
    INDEX
    Explanations

    humorous, sassy, crime, politics, fiction writers

    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
    ä½ľä¸º
    -0.06
    ely
    -0.06
    é¦ĸå°Ķ
    -0.05
    wegen
    -0.05
    iale
    -0.05
    -regexp
    -0.05
    által
    -0.05
    -re
    -0.05
    å°Ĩå°±
    -0.05
    åĻ
    -0.05
    POSITIVE LOGITS
    家åĸ»
    0.06
    åı¯æĥ³
    0.05
    utow
    0.05
    æģIJ
    0.05
     unfavor
    0.05
    ุà¸Ļ
    0.05
     Ring
    0.05
    ring
    0.05
    è¾ĥçŁŃ
    0.05
    -bl
    0.05
    Activations Density 0.002%

    No Known Activations