© 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. 18-TRANSCODER-HP
    7. 89728
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alchemy
    -0.29
    è¯ķ管
    -0.28
     bergen
    -0.28
    左边
    -0.25
    tar
    -0.25
    zyst
    -0.25
    ransition
    -0.25
    çŀ°
    -0.25
    è´Łè´£
    -0.25
    PLICIT
    -0.24
    POSITIVE LOGITS
    ixin
    0.27
     dn
    0.27
    ld
    0.24
    itched
    0.24
    ppo
    0.24
    ansa
    0.24
    Checked
    0.23
    atoria
    0.23
    lected
    0.23
    owell
    0.23
    Activations Density 2.322%

    No Known Activations

    This feature has no known activations.