© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19714
    Prev
    Next
    INDEX
    Explanations

    this or that choice

    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
    unk
    -0.06
     nonetheless
    -0.06
     nevertheless
    -0.05
    äºijå±±
    -0.05
    ne
    -0.05
    ce
    -0.05
    çĬ¹
    -0.05
    离
    -0.05
    struct
    -0.05
    ä¼Ĺ
    -0.05
    POSITIVE LOGITS
    ][(
    0.07
    åѦæľīæīĢ
    0.06
    Ú©Ø´
    0.06
    _DEFINE
    0.06
    夥
    0.06
    sprozess
    0.06
    æīijéĿ¢èĢĮæĿ¥
    0.06
    صÙģ
    0.06
    [âĢ¦
    0.06
    ",-
    0.05
    Activations Density 0.051%

    No Known Activations