© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    to say that

    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
    **”,
    -0.06
    Cho
    -0.06
     urat
    -0.06
    dür
    -0.06
     ÅŁans
    -0.06
    fristig
    -0.06
    füh
    -0.06
    .";
    -0.05
    !”.
    -0.05
    ä¸İæĤ¨
    -0.05
    POSITIVE LOGITS
     bla
    0.06
    aler
    0.05
     past
    0.05
    ala
    0.05
    bla
    0.05
    unge
    0.05
    entr
    0.05
    æ´ŀ
    0.05
    ale
    0.05
    rom
    0.05
    Activations Density 0.001%

    No Known Activations