© 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. 22030
    Prev
    Next
    INDEX
    Explanations

    implementing or executing actions

    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
    undle
    -0.05
    amt
    -0.05
    se
    -0.05
     едини
    -0.05
     de
    -0.04
    åİŁå®¡
    -0.04
     con
    -0.04
    :
    -0.04
     gener
    -0.04
    åĢĻ
    -0.04
    POSITIVE LOGITS
    oriously
    0.07
    pä
    0.07
     airst
    0.07
    apest
    0.07
    æī§è¡ĮåĬĽ
    0.07
     matériels
    0.07
    aldi
    0.07
    縮
    0.07
    undry
    0.07
    IFEST
    0.07
    Activations Density 0.016%

    No Known Activations