© 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. 40232
    Prev
    Next
    INDEX
    Explanations

    .IOException

    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
     geg
    -0.28
     representative
    -0.27
    è¿Ļ个éĹ®é¢ĺ
    -0.27
    éĢĢåĩº
    -0.26
     dr
    -0.25
    EP
    -0.25
    ä¹ŁåºĶ该
    -0.24
    èĩ³æĸ¼
    -0.24
    rup
    -0.24
     Representative
    -0.23
    POSITIVE LOGITS
    arking
    0.28
    ilate
    0.28
    irectional
    0.28
     IMDb
    0.26
    /title
    0.26
    åŁİ
    0.26
    æłĩé¢ĺ
    0.25
     Attr
    0.25
    pageTitle
    0.25
     selectively
    0.25
    Activations Density 0.023%

    No Known Activations