© 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. 24619
    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
    èĢ¿
    -0.28
    rlen
    -0.27
     card
    -0.27
    fact
    -0.25
     thụ
    -0.25
    缸åħ³æĸ°éĹ»
    -0.25
    æĬ½
    -0.24
    plode
    -0.24
    roc
    -0.24
    çĵľ
    -0.24
    POSITIVE LOGITS
    RING
    0.31
    æĮ½
    0.28
     Apostle
    0.28
    ring
    0.27
    igers
    0.26
    .eof
    0.26
    -Up
    0.25
    apes
    0.25
    rollable
    0.24
    جÙĩ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.