© 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. 89160
    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
    ):-
    -0.28
    FIELDS
    -0.25
    ثر
    -0.24
    ElementsBy
    -0.24
    _PHP
    -0.24
    çł
    -0.23
     Cay
    -0.23
    _ur
    -0.23
     +-
    -0.23
    ADR
    -0.23
    POSITIVE LOGITS
    ordinate
    0.27
    haar
    0.26
    omatic
    0.26
    yt
    0.25
     propTypes
    0.25
    ytic
    0.25
    å»¶æľŁ
    0.25
    way
    0.24
    å¼ı
    0.24
    ests
    0.24
    Activations Density 0.154%

    No Known Activations

    This feature has no known activations.