© 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. 20-TRANSCODER-HP
    7. 142188
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trace
    -0.33
    Trace
    -0.32
    .trace
    -0.30
    akan
    -0.30
     largely
    -0.29
     Trace
    -0.29
    _trace
    -0.28
    estone
    -0.28
     primarily
    -0.27
    (trace
    -0.27
    POSITIVE LOGITS
    ä»Ĺ
    0.28
     \@
    0.26
    urate
    0.25
    é«®
    0.25
     DAMAGES
    0.24
    ãĤ¤
    0.24
    éŀĺ
    0.24
    æĹĨ
    0.24
    @\
    0.23
    ~,
    0.23
    Activations Density 16.036%

    No Known Activations

    This feature has no known activations.