© 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. 89735
    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
     Fancy
    -0.25
     inherit
    -0.25
    OSC
    -0.25
    继æī¿
    -0.25
     diam
    -0.24
    compound
    -0.24
    OND
    -0.24
    ä¸Ńæłĩ
    -0.24
     removeAll
    -0.23
    riors
    -0.23
    POSITIVE LOGITS
     Prix
    0.26
    akens
    0.24
    king
    0.24
    ä¿ĥè¿Ľ
    0.24
     Observatory
    0.24
    ota
    0.24
    elon
    0.24
    á»ħn
    0.24
    enis
    0.24
    lid
    0.24
    Activations Density 11.277%

    No Known Activations

    This feature has no known activations.