© 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. 18-TRANSCODER-HP
    7. 88740
    Prev
    Next
    INDEX
    Explanations

    Unstructured writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assumes
    -0.35
    ume
    -0.29
    ass
    -0.28
    adora
    -0.27
     prac
    -0.26
    ürn
    -0.25
    adoras
    -0.25
     Society
    -0.25
    quent
    -0.25
    usi
    -0.24
    POSITIVE LOGITS
    解æĶ¾åĨĽ
    0.29
    classify
    0.26
     stay
    0.26
    incip
    0.26
    çľģéĴ±
    0.25
    kees
    0.25
     stays
    0.25
     stayed
    0.24
    izont
    0.24
     staying
    0.24
    Activations Density 4.427%

    No Known Activations