© 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. 40530
    Prev
    Next
    INDEX
    Explanations

    traffic

    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
    etro
    -0.28
    åĹĶ
    -0.26
     Bureau
    -0.25
    terror
    -0.25
    keh
    -0.24
    交éĢļè¿IJè¾ĵ
    -0.24
    nowrap
    -0.23
    udp
    -0.23
    odom
    -0.23
    ngth
    -0.23
    POSITIVE LOGITS
    aland
    0.29
    าà¸ĩ
    0.28
    hä
    0.28
    ä»Ģ
    0.27
     punt
    0.27
     FIN
    0.26
     proprio
    0.25
     FUNC
    0.25
    åĩºèµĦ
    0.24
    å®ī举
    0.24
    Activations Density 0.122%

    No Known Activations