© 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. 22158
    Prev
    Next
    INDEX
    Explanations

    member or officer

    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
     challenging
    -0.06
    å¡«è¡¥
    -0.06
     I
    -0.05
     discovery
    -0.05
    osi
    -0.05
     new
    -0.05
    or
    -0.05
     discover
    -0.04
     compens
    -0.04
    tk
    -0.04
    POSITIVE LOGITS
     Cuma
    0.07
    kala
    0.07
     nowhere
    0.06
    aires
    0.06
    édi
    0.06
     Copies
    0.06
    nyata
    0.06
    weapon
    0.06
    人人
    0.06
    tract
    0.06
    Activations Density 0.001%

    No Known Activations