© 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. 24827
    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
    å±ķé¦Ĩ
    -0.26
    heim
    -0.26
    ì°į
    -0.25
     home
    -0.24
     Int
    -0.24
     Love
    -0.24
    èĩªåĬ©
    -0.23
     Hell
    -0.23
     Platt
    -0.23
    ÎĴ
    -0.23
    POSITIVE LOGITS
    odi
    0.28
    ngen
    0.28
    åİĨ
    0.27
    angling
    0.25
    á»ĩp
    0.25
    pressão
    0.25
    adier
    0.24
    allon
    0.24
    folios
    0.24
    wal
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.