© 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. 25-TRANSCODER-HP
    7. 108913
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aris
    -0.26
    太éĺ³
    -0.25
    æľĢ好
    -0.24
     App
    -0.24
     pe
    -0.24
    çĤī
    -0.24
    n
    -0.23
    ç²īå°ĺ
    -0.23
     stere
    -0.23
     poll
    -0.23
    POSITIVE LOGITS
    rollo
    0.28
     Bolton
    0.27
    edin
    0.25
    xon
    0.25
     xbox
    0.24
    OLS
    0.24
     Norris
    0.24
    itional
    0.24
    redo
    0.24
    oshi
    0.23
    Activations Density 0.088%

    No Known Activations

    This feature has no known activations.