© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20175
    Prev
    Next
    INDEX
    Explanations

    study or investigate

    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
    práv
    -0.06
    çļĦå°ıç¼ĸ
    -0.06
    ÂŃt
    -0.06
     revi
    -0.06
    Ñijм
    -0.06
    æĿ±åįĹ
    -0.06
    zent
    -0.05
    jedn
    -0.05
    új
    -0.05
     masturbating
    -0.05
    POSITIVE LOGITS
    lace
    0.06
    illo
    0.05
    åIJĹ
    0.05
    ization
    0.05
    ä½³
    0.05
    éĤ£ç§į
    0.05
    ÙĬبة
    0.05
    说æĺİ
    0.05
    çĻ¾åħ¬éĩĮ
    0.05
    æĹı
    0.05
    Activations Density 0.109%

    No Known Activations