© 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. 40548
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    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
    齡
    -0.29
     Garrison
    -0.28
    é¬ĵ
    -0.27
    åĽŁ
    -0.27
    é¾Ħ
    -0.26
    units
    -0.25
    èµĽåĮº
    -0.25
     autoFocus
    -0.25
    odate
    -0.24
    祼
    -0.24
    POSITIVE LOGITS
    ackers
    0.29
    rh
    0.28
     Vert
    0.26
     ama
    0.26
     half
    0.26
    fork
    0.26
    ju
    0.26
     inter
    0.25
     SY
    0.25
    论
    0.25
    Activations Density 0.129%

    No Known Activations