© 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. 32-TRANSCODER-HP
    7. 42981
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èłĸ
    -0.28
    æī¼
    -0.27
    è½®
    -0.26
     Kaplan
    -0.25
    ieri
    -0.25
     Ace
    -0.25
    eken
    -0.25
     Urb
    -0.24
    lights
    -0.24
    internal
    -0.24
    POSITIVE LOGITS
     createContext
    0.26
     $?
    0.26
    па
    0.23
    _conditions
    0.23
    OnChange
    0.23
    onde
    0.23
    paces
    0.23
    好æĦŁ
    0.23
     Scarlet
    0.23
    姬
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.