© 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. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7448
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éªĮ
    -0.27
    æݧèĤ¡éĽĨåĽ¢
    -0.26
    çīĩ
    -0.25
    æį»
    -0.25
    åı¯ä»¥çĶ¨
    -0.25
    enty
    -0.24
    isor
    -0.23
    主æīĵ
    -0.23
    ç»ĵ论
    -0.23
    çģĮ
    -0.23
    POSITIVE LOGITS
    umed
    0.29
     Pais
    0.27
     tread
    0.27
    itta
    0.27
    bru
    0.26
    spar
    0.25
    è¿°
    0.25
    izziness
    0.25
    rien
    0.24
     Credits
    0.24
    Activations Density 0.038%

    No Known Activations