© 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. 88576
    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
     Flesh
    -0.28
    æĥ³æī¾
    -0.26
    æħ°
    -0.25
    éĻ¢éĻ¢éķ¿
    -0.25
     Venue
    -0.25
    imary
    -0.24
    Venue
    -0.24
    ÑĢеб
    -0.23
     unrecognized
    -0.23
     MOZ
    -0.23
    POSITIVE LOGITS
     pun
    0.29
    hq
    0.26
    mia
    0.25
    åħī彩
    0.25
     wink
    0.25
    ail
    0.24
    ster
    0.24
    lo
    0.24
     everlasting
    0.24
    oken
    0.24
    Activations Density 11.674%

    No Known Activations

    This feature has no known activations.