© 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. 24846
    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
    .Manifest
    -0.26
    ||(
    -0.26
    åijľ
    -0.25
    <footer
    -0.24
    wart
    -0.24
     Guid
    -0.24
    äsent
    -0.23
     skulls
    -0.23
     Bes
    -0.23
    adow
    -0.23
    POSITIVE LOGITS
    lian
    0.28
    >Title
    0.26
    çĶŁæĢģåľĪ
    0.24
    uje
    0.24
    void
    0.24
    éļĶ离
    0.24
    opause
    0.24
    âĸĦ
    0.24
    peng
    0.23
    اة
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.