© 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. 89105
    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
    dge
    -0.26
     dah
    -0.26
    sworth
    -0.25
    atted
    -0.25
    InView
    -0.24
    æ¯Ĺ
    -0.24
     Wes
    -0.24
    æĻ
    -0.24
    çīµ
    -0.24
    Preview
    -0.24
    POSITIVE LOGITS
    po
    0.30
    è¾Ī
    0.27
    tor
    0.26
     mell
    0.25
    輩
    0.25
    PO
    0.25
    æ·ĭ
    0.24
     tor
    0.24
    å£
    0.24
    Ready
    0.24
    Activations Density 0.154%

    No Known Activations

    This feature has no known activations.