© 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. 129447
    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
     URL
    -0.26
    ORITY
    -0.26
     .
    -0.25
     post
    -0.25
    _OW
    -0.24
     Erf
    -0.24
     rec
    -0.24
    ular
    -0.24
     refl
    -0.24
    BaseUrl
    -0.24
    POSITIVE LOGITS
     inherits
    0.27
    颤æĬĸ
    0.27
    edy
    0.27
    éķ¿éķ¿
    0.25
    åIJĮå¿ĥ
    0.25
    åĨįè§ģ
    0.25
     catholic
    0.25
     gode
    0.25
    åı¯æĢķçļĦ
    0.24
    god
    0.24
    Activations Density 8.557%

    No Known Activations

    This feature has no known activations.