© 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. 23-TRANSCODER-HP
    7. 25052
    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
    dish
    -0.27
    ells
    -0.25
    æĬķèµĦåŁºéĩij
    -0.24
     purpose
    -0.24
    elt
    -0.24
    Ｋ
    -0.24
     sequence
    -0.23
    part
    -0.23
    çĿ
    -0.23
    STALL
    -0.23
    POSITIVE LOGITS
     Fet
    0.28
    è´¢
    0.28
    Edition
    0.25
    æĢ§åij½
    0.25
    erra
    0.25
     acquiring
    0.24
    <Transform
    0.24
    lä
    0.24
    lemen
    0.23
    rina
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.