© 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. 21487
    Prev
    Next
    INDEX
    Explanations

    devoted to / focused on

    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
     Einblick
    -0.05
    å¤ļå°ij
    -0.05
    ioen
    -0.05
     sez
    -0.05
    ático
    -0.05
    azio
    -0.05
    jne
    -0.05
    éĢģäºĨ
    -0.05
    åł¡
    -0.05
    anza
    -0.05
    POSITIVE LOGITS
    ale
    0.07
    uell
    0.06
    irse
    0.06
    stens
    0.06
    wier
    0.06
    vre
    0.05
    ir
    0.05
    vert
    0.05
    ire
    0.05
    ä¸įåİ»
    0.05
    Activations Density 0.033%

    No Known Activations