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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161822
    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
    ampo
    -0.29
     neutral
    -0.27
    uen
    -0.25
     Neutral
    -0.24
    ipo
    -0.24
    æģŃåĸľ
    -0.24
    (cont
    -0.24
    amber
    -0.23
    å±ij
    -0.23
    arella
    -0.23
    POSITIVE LOGITS
    llx
    0.32
    cision
    0.25
    ptune
    0.23
    çİĩè¾¾
    0.23
    rhs
    0.23
    kernel
    0.23
    -percent
    0.23
    Ãłng
    0.23
    lhs
    0.23
     kernel
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.