© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163359
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cc
    -0.29
    åĬ¨çī©
    -0.28
    ec
    -0.27
     me
    -0.26
    [
    -0.26
     normal
    -0.26
    g
    -0.26
    ale
    -0.26
     <
    -0.25
     [
    -0.25
    POSITIVE LOGITS
    pla
    0.28
    rowned
    0.27
     Armour
    0.25
     Plex
    0.25
    +":
    0.25
    пл
    0.25
    joined
    0.25
    visor
    0.24
    ·»
    0.24
    eros
    0.24
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.