© 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. 20670
    Prev
    Next
    INDEX
    Explanations

    slices of food

    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
    undu
    -0.06
    æĮĩå®ļåľ°çĤ¹
    -0.06
    què
    -0.06
    çī¹åĭĴ
    -0.06
    rough
    -0.06
     gosto
    -0.06
    roma
    -0.06
    quoi
    -0.06
    ارة
    -0.06
    umuz
    -0.06
    POSITIVE LOGITS
    es
    0.07
     enduring
    0.07
    åĦ¿çļĦ
    0.06
    å¼ĢæĿ¥
    0.06
    åĦ¿
    0.06
    esn
    0.06
    æĹ¢
    0.06
    en
    0.06
    otyp
    0.05
     thinly
    0.05
    Activations Density 0.005%

    No Known Activations