© 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. 40615
    Prev
    Next
    INDEX
    Explanations

    scientific references

    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
     Genius
    -0.29
    ä¸İæѤ
    -0.26
     Fior
    -0.25
    ajÄħ
    -0.25
    ãĤ¡
    -0.24
    åºĶçĶ¨
    -0.24
    .module
    -0.24
     Twe
    -0.23
    anno
    -0.23
    åİ»äºĨ
    -0.23
    POSITIVE LOGITS
     postfix
    0.29
     GetName
    0.26
     uÄŁ
    0.26
    æĻļæĬ¥
    0.26
    MDB
    0.25
    isz
    0.25
    yny
    0.25
    nal
    0.24
    æģ¶å¿ĥ
    0.23
    èIJ½ä¸ĭ
    0.23
    Activations Density 2.200%

    No Known Activations