© 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. 63558
    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
    uron
    -0.32
    oton
    -0.30
     unh
    -0.27
    åĪĩ
    -0.27
    ulton
    -0.27
    ython
    -0.26
    ARC
    -0.26
    åºŃ
    -0.26
    ctx
    -0.25
    hin
    -0.25
    POSITIVE LOGITS
    éħĤ
    0.25
    æ¢ĥ
    0.25
    çĪĨ款
    0.24
    尾巴
    0.24
     示
    0.23
    _interest
    0.23
    æĶ¯æŁ±
    0.23
    Parameter
    0.23
    alty
    0.23
    å½¢æĢģ
    0.23
    Activations Density 1.361%

    No Known Activations

    This feature has no known activations.