© 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. 89406
    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
    akash
    -0.25
    woman
    -0.23
     disciplines
    -0.23
    ãĥ¬ãĥĵãĥ¥ãĥ¼
    -0.23
    zy
    -0.22
    æķ´è½¦
    -0.22
     $("#"
    -0.21
    è¿Ļç¯ĩ
    -0.21
    hover
    -0.21
     cust
    -0.21
    POSITIVE LOGITS
     pcs
    0.28
    pcs
    0.28
    /fr
    0.27
    oupper
    0.26
    imary
    0.25
    æݨ广
    0.25
    ENCY
    0.24
    _FR
    0.23
     trans
    0.23
     Dem
    0.23
    Activations Density 0.353%

    No Known Activations

    This feature has no known activations.