© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40019
    Prev
    Next
    INDEX
    Explanations

    quantity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _WORD
    -0.28
    ä½¥
    -0.27
    igkeit
    -0.27
    TickCount
    -0.26
    ä¸įä¸ĭ
    -0.26
    emean
    -0.24
    eced
    -0.24
    овиÑĩ
    -0.24
    icks
    -0.24
    ied
    -0.23
    POSITIVE LOGITS
    主管
    0.28
    allas
    0.27
    osto
    0.25
    åıįæĺłåĩº
    0.25
     fas
    0.24
     lil
    0.24
    sheets
    0.24
    cala
    0.24
     widest
    0.24
    neo
    0.23
    Activations Density 0.209%

    No Known Activations