© 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. 18333
    Prev
    Next
    INDEX
    Explanations

    `current` date, `screen`plays, `books`, `Community`

    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
    æķħ人
    -0.06
     Ñĥд
    -0.06
    agne
    -0.06
    åı¶
    -0.06
    端çļĦ
    -0.05
     Linden
    -0.05
    çī¹æľī
    -0.05
    ern
    -0.05
    æĺ
    -0.05
    é¡¿
    -0.05
    POSITIVE LOGITS
    ÙĪÙĨÙĩ
    0.06
    วา
    0.05
    /of
    0.05
    ä¸įçĿĢ
    0.05
    以任ä½ķ
    0.05
    çĪ±æĪij
    0.05
    اÙĨÙĩ
    0.05
    æ¡Ī
    0.05
    ık
    0.05
    Xã
    0.05
    Activations Density 0.059%

    No Known Activations