© 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. 89548
    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
    Services
    -0.28
    Clone
    -0.28
    enate
    -0.27
    åħĭæĢĿ
    -0.27
    _clone
    -0.27
    persistent
    -0.25
    -prepend
    -0.24
    clone
    -0.24
    ocate
    -0.24
     racked
    -0.24
    POSITIVE LOGITS
     corners
    0.27
    aż
    0.26
    bout
    0.26
    abilia
    0.25
    èŃ
    0.25
    agraph
    0.25
    .createObject
    0.25
    ometry
    0.24
    ÅŁt
    0.24
    -corner
    0.24
    Activations Density 11.765%

    No Known Activations

    This feature has no known activations.