© 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. 22-TRANSCODER-HP
    7. 98217
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    em
    -0.29
    ear
    -0.28
    SF
    -0.26
    HH
    -0.25
    ISTR
    -0.23
    ening
    -0.23
    _null
    -0.23
    rd
    -0.23
    abs
    -0.23
    åıĬ以ä¸Ĭ
    -0.23
    POSITIVE LOGITS
     Depths
    0.29
    uzu
    0.26
    dle
    0.24
    pez
    0.23
    å¢ŀéķ¿çİĩ
    0.23
    没åħ³ç³»
    0.23
     wholesome
    0.22
    dent
    0.22
    arez
    0.22
    é¡¿
    0.22
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.