© 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. 63572
    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
     миÑĢов
    -0.24
    .navigation
    -0.24
     =>'
    -0.24
    延
    -0.24
     ---
    -0.24
     Reached
    -0.23
    rg
    -0.23
    éĿŀ常
    -0.23
    ä½Ļ
    -0.23
    åį³æŶ
    -0.23
    POSITIVE LOGITS
     FF
    0.26
    åķĨä¸ļåľ°äº§
    0.26
     Castillo
    0.25
    sdk
    0.25
    dì
    0.25
    quil
    0.24
    dni
    0.24
    chan
    0.24
    éĹ´éļĶ
    0.24
    建çŃij设计
    0.24
    Activations Density 25.213%

    No Known Activations

    This feature has no known activations.