© 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. 20053
    Prev
    Next
    INDEX
    Explanations

    counting in texts about groups

    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
    aday
    -0.06
     latter
    -0.06
    第äºĮ个
    -0.06
    essler
    -0.06
    ختÙĩ
    -0.06
    诸
    -0.05
     loại
    -0.05
    lair
    -0.05
    åıĪæĬĬ
    -0.05
     Hague
    -0.05
    POSITIVE LOGITS
     grop
    0.06
    åĬłæĭ¿å¤§
    0.06
    ÑĢое
    0.05
     analytic
    0.05
    ELSE
    0.05
    ven
    0.05
    æĺ¯éĽĨ
    0.05
    ross
    0.05
    ׳×Ķ
    0.05
    å°ļ
    0.05
    Activations Density 0.042%

    No Known Activations