© 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. 23-TRANSCODER-HP
    7. 23834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rouch
    -0.25
    å¿łå®ŀ
    -0.24
    ãģĦãģŁ
    -0.24
    åģľ
    -0.24
    _STRUCTURE
    -0.23
    åĩĨå¤ĩ
    -0.23
    dden
    -0.23
    Ãītat
    -0.23
    OnError
    -0.23
     اÙĦÙħÙĤدس
    -0.23
    POSITIVE LOGITS
     Asc
    0.29
    .asc
    0.28
     asc
    0.27
     escal
    0.26
    atak
    0.26
    ADB
    0.26
    _asc
    0.26
    asc
    0.26
     Constant
    0.25
    Asc
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.