© 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. 39917
    Prev
    Next
    INDEX
    Explanations

    Article and Code Snippets

    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
     Half
    -0.29
     Atlas
    -0.26
    .writeString
    -0.26
     half
    -0.25
    åĪĽæĸ°èĥ½åĬĽ
    -0.25
     sno
    -0.25
     atlas
    -0.24
    åĪłéĻ¤æĪIJåĬŁ
    -0.24
     crafts
    -0.24
    åĩłåı¥
    -0.24
    POSITIVE LOGITS
    åı¯çĶ¨
    0.26
    æĦı大åĪ©
    0.26
    桧
    0.25
    aleigh
    0.25
    ment
    0.24
     jes
    0.24
    (pref
    0.23
    neh
    0.23
    udge
    0.23
    edef
    0.23
    Activations Density 1.008%

    No Known Activations