© 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. 25169
    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
    .semantic
    -0.31
    jac
    -0.26
    ieg
    -0.26
     Ø£Ùħ
    -0.25
    ick
    -0.25
    rc
    -0.25
    eden
    -0.24
    ite
    -0.24
    rx
    -0.24
    jdk
    -0.24
    POSITIVE LOGITS
     plaque
    0.27
    ź
    0.26
    æį¢æĪIJ
    0.26
    ibia
    0.26
    ç²ī
    0.25
    elpers
    0.25
    ulates
    0.25
    cribes
    0.25
     respected
    0.25
    witch
    0.25
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.