© 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. 89135
    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
     phá
    -0.27
    Disallow
    -0.27
    advertisement
    -0.26
     isSuccess
    -0.26
    classList
    -0.24
    reland
    -0.23
    æij¹
    -0.23
    abileceÄŁi
    -0.23
    ipa
    -0.23
    rig
    -0.23
    POSITIVE LOGITS
     Exped
    0.30
    enÃŃ
    0.28
     leash
    0.27
    assy
    0.26
    erview
    0.26
    _mx
    0.26
    ody
    0.25
    xor
    0.25
     Nom
    0.25
    ãģ¦ãģĬãĤĬ
    0.24
    Activations Density 5.545%

    No Known Activations

    This feature has no known activations.