© 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. 20995
    Prev
    Next
    INDEX
    Explanations

    declaration of public class or namespace

    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
    izable
    -0.07
    ar
    -0.07
    Wür
    -0.06
    eroy
    -0.06
    étique
    -0.06
    ière
    -0.05
    ery
    -0.05
    tract
    -0.05
    ers
    -0.05
    sign
    -0.05
    POSITIVE LOGITS
    ãģ¾ãģ¾
    0.08
    ़
    0.07
    çĦ¶æĺ¯
    0.07
    oriously
    0.07
    ellaneous
    0.06
    maken
    0.06
    çĦ¶çļĦ
    0.06
    tease
    0.06
    iamond
    0.06
    enen
    0.06
    Activations Density 0.081%

    No Known Activations