© 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. 18145
    Prev
    Next
    INDEX
    Explanations

    this one

    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
    ç»Ĵ
    -0.05
    amina
    -0.05
    æĬĢæľ¯æīĭ段
    -0.05
    è¯ķåĽ¾
    -0.05
    çļĦæĶ¹åıĺ
    -0.05
    èµ·åĽł
    -0.05
    ấu
    -0.05
    ologne
    -0.05
     riv
    -0.05
    SEE
    -0.05
    POSITIVE LOGITS
    她们çļĦ
    0.06
     ups
    0.06
    ä»ĸ们çļĦ
    0.06
    orado
    0.06
    gi
    0.05
    repo
    0.05
    éĹ´æİ¥
    0.05
     ihren
    0.05
    èĤĦ
    0.05
    çīĻ
    0.05
    Activations Density 0.001%

    No Known Activations