© 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. 40675
    Prev
    Next
    INDEX
    Explanations

    News/legal text

    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
    omnia
    -0.28
     mot
    -0.26
    好åĿı
    -0.26
    erland
    -0.26
     mote
    -0.26
     phê
    -0.25
    peria
    -0.25
     pert
    -0.25
     neg
    -0.25
    奥æŀĹåĮ¹
    -0.25
    POSITIVE LOGITS
    .fromLTRB
    0.26
    Symfony
    0.26
    -than
    0.25
    èºį
    0.25
    cents
    0.24
    æIJľ
    0.24
    对æĪijæĿ¥è¯´
    0.23
     Seiten
    0.23
    .break
    0.23
     clo
    0.23
    Activations Density 0.119%

    No Known Activations