© 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. 21570
    Prev
    Next
    INDEX
    Explanations

    xe, JJ, *x, *k

    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
    leih
    -0.06
    人已
    -0.06
    ä¸ĢåĪĻ
    -0.06
    ewe
    -0.06
    Ẩ
    -0.06
    uzz
    -0.06
     tenue
    -0.06
    ews
    -0.06
     añ
    -0.05
     Tent
    -0.05
    POSITIVE LOGITS
    åĪĨç±»
    0.05
    强è°ĥ
    0.05
    ç»ı常
    0.05
    odom
    0.05
    éģĹæ¼ı
    0.05
    æĮij
    0.05
    让æĪij
    0.05
    pack
    0.05
    çĨĬ
    0.05
    åĽ¢éķ¿
    0.05
    Activations Density 0.002%

    No Known Activations