© 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. 19181
    Prev
    Next
    INDEX
    Explanations

    sauce

    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
    ories
    -0.06
    ÑĤел
    -0.06
    ecież
    -0.06
    nale
    -0.06
    åħ¶ä»ĸæĸ¹å¼ı
    -0.05
    bole
    -0.05
    åĵī
    -0.05
    -stat
    -0.05
    contrib
    -0.05
    channels
    -0.05
    POSITIVE LOGITS
    åĮħåIJĥ
    0.06
    ing
    0.06
    ção
    0.06
     Kediri
    0.06
    anom
    0.06
    quin
    0.06
    obra
    0.06
    engel
    0.06
    otion
    0.06
    ãģŁãĤĭ
    0.06
    Activations Density 0.002%

    No Known Activations