© 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. 19511
    Prev
    Next
    INDEX
    Explanations

    tunnel vision

    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
    epend
    -0.06
    ervers
    -0.05
    å¼łåĽ¾çīĩ
    -0.05
    çĹĩ
    -0.05
    æű
    -0.05
    ark
    -0.05
    ึà¹Īà¸ĩ
    -0.05
    enn
    -0.05
    icias
    -0.05
    ém
    -0.05
    POSITIVE LOGITS
    åıĻ
    0.07
     overlook
    0.06
    è¡Ķ
    0.06
    忽çķ¥äºĨ
    0.06
    adesh
    0.06
    ISTER
    0.06
    æķĺ
    0.06
    忽çķ¥
    0.06
    Ñĸл
    0.06
    inov
    0.06
    Activations Density 0.038%

    No Known Activations