© 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. 19-TRANSCODER-HP
    7. 9251
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ATOMIC
    -0.29
    èĬĤ
    -0.28
    é¢Ĩ
    -0.28
    å²Ń
    -0.27
    åİĭ
    -0.26
    æ³ķå®ļ
    -0.26
    iet
    -0.26
     multis
    -0.26
    è°ĥ
    -0.26
    pect
    -0.25
    POSITIVE LOGITS
    CKER
    0.31
    cker
    0.30
    ,proto
    0.27
    /Error
    0.26
    uger
    0.25
    -turned
    0.25
    ResourceId
    0.24
    izedName
    0.24
    举æĬ¥çĶµè¯Ŀ
    0.24
    /close
    0.23
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.