© 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. 41318
    Prev
    Next
    INDEX
    Explanations

    Code and configurations

    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
    itel
    -0.31
    å¸Ī
    -0.27
    çű
    -0.27
     Cin
    -0.26
    bic
    -0.25
    eel
    -0.25
     poisoned
    -0.25
    鼶åĶ®åķĨ
    -0.24
    acen
    -0.24
    éĽĨåĽ¢èĤ¡ä»½
    -0.24
    POSITIVE LOGITS
     pronounced
    0.27
    wart
    0.25
    åłĤ
    0.25
    âĢ¦âĢ¦
    0.25
    imals
    0.24
    æĶ¾
    0.24
    -aos
    0.24
    ä¸įæĢķ
    0.23
    ——
    0.23
    ãĢĤ“
    0.23
    Activations Density 0.154%

    No Known Activations