© 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. 107245
    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
    oris
    -0.28
     ((_
    -0.28
    便ä¼ļ
    -0.27
    isms
    -0.27
    isma
    -0.26
    _called
    -0.26
    便åı¯
    -0.26
    _VC
    -0.25
    [_
    -0.25
    antium
    -0.25
    POSITIVE LOGITS
    ir
    0.27
    acute
    0.27
    irate
    0.26
    ika
    0.26
    åĩºçīĪ
    0.26
    iran
    0.26
    atz
    0.26
    (s
    0.24
    ening
    0.24
    åį¡
    0.24
    Activations Density 8.547%

    No Known Activations

    This feature has no known activations.