© 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. 18386
    Prev
    Next
    INDEX
    Explanations

    search functionality or results

    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
     access
    -0.05
    olland
    -0.05
    .cgi
    -0.05
    ussi
    -0.05
     عÙĦا
    -0.05
    æ¡ĪçĶ±
    -0.05
     es
    -0.05
    los
    -0.05
     layered
    -0.04
     solid
    -0.04
    POSITIVE LOGITS
    аб
    0.06
     terc
    0.06
    zinha
    0.06
    rena
    0.06
    rud
    0.06
     slugg
    0.06
    ë°Ľ
    0.06
    鼨èĬ±
    0.06
    cón
    0.06
    uel
    0.06
    Activations Density 0.031%

    No Known Activations