© 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. 107937
    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
    coni
    -0.28
     pair
    -0.26
    GetData
    -0.25
    GetType
    -0.25
    Girls
    -0.24
    anted
    -0.24
    Type
    -0.24
    ires
    -0.24
    emailer
    -0.23
    å®ĥåı¯ä»¥
    -0.23
    POSITIVE LOGITS
    çĸı
    0.30
    主ä½ĵ
    0.29
    itty
    0.26
    (subject
    0.26
    åIJ¼
    0.25
    _SUBJECT
    0.25
    subjects
    0.24
     Subject
    0.24
    ril
    0.24
     subjects
    0.23
    Activations Density 11.962%

    No Known Activations

    This feature has no known activations.