© 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. 89374
    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
    prox
    -0.28
    lever
    -0.25
    ahn
    -0.24
     spiked
    -0.24
     suspension
    -0.23
     swept
    -0.23
    åıĹçĽĬ
    -0.23
    çļĦåľ°ä½į
    -0.23
    ine
    -0.23
     erst
    -0.23
    POSITIVE LOGITS
    -seat
    0.30
    çĦ¦
    0.29
    heimer
    0.28
    ä¸ĵ注äºİ
    0.25
     seal
    0.25
    Marshal
    0.25
    èĥ¶
    0.25
     focal
    0.25
     Raid
    0.24
    med
    0.24
    Activations Density 18.470%

    No Known Activations

    This feature has no known activations.