© 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. 35-TRANSCODER-HP
    7. 40341
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -0.42
    n
    -0.39
    g
    -0.38
    2
    -0.38
    3
    -0.37
    x
    -0.37
    re
    -0.36
    m
    -0.35
    1
    -0.34
    4
    -0.34
    POSITIVE LOGITS
    thalm
    0.33
    <quote
    0.32
    "struct
    0.29
    ughters
    0.28
     Gutenberg
    0.27
    aeda
    0.27
    senal
    0.27
    ulares
    0.26
    ascar
    0.26
     Dom
    0.26
    Activations Density 8.613%

    No Known Activations

    This feature has no known activations.