© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20213
    Prev
    Next
    INDEX
    Explanations

    BR

    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
    ubil
    -0.06
    ensiones
    -0.06
    ek
    -0.06
    å¥½åľ¨
    -0.06
    sburg
    -0.06
    stood
    -0.06
    ä¸įè¿ľ
    -0.05
     عÙģ
    -0.05
    ./.
    -0.05
    设计é£İæł¼
    -0.05
    POSITIVE LOGITS
     cass
    0.06
    æĬĬ人
    0.05
     Sanford
    0.05
    erts
    0.05
    undo
    0.05
     Aspect
    0.05
    uel
    0.05
     condol
    0.05
    HB
    0.05
    eras
    0.05
    Activations Density 0.001%

    No Known Activations