© 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. 89611
    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
     yourselves
    -0.26
    ẹ
    -0.26
     cages
    -0.25
    ried
    -0.24
    履约
    -0.24
    instrument
    -0.24
    andy
    -0.24
     UIStoryboard
    -0.24
    âĢ¦”↵↵
    -0.24
     Aydın
    -0.24
    POSITIVE LOGITS
    éĢļ常æĺ¯
    0.26
    orges
    0.25
     however
    0.24
    温
    0.24
    IRT
    0.23
     num
    0.22
    RIPT
    0.22
    <num
    0.22
    ала
    0.22
    Num
    0.22
    Activations Density 9.947%

    No Known Activations

    This feature has no known activations.