© 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. 32-TRANSCODER-HP
    7. 43198
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Destruction
    -0.30
    ä¸įèĪį
    -0.26
     DEST
    -0.25
    elic
    -0.24
    å¸ĪèĮĥ
    -0.24
     Ind
    -0.24
    è¿Ļ个èģĮä¸ļ
    -0.24
    vore
    -0.24
    ona
    -0.23
     Au
    -0.23
    POSITIVE LOGITS
    èĢĮ
    0.43
    èĢĮåľ¨
    0.34
    iad
    0.33
     while
    0.31
     whereas
    0.30
    While
    0.30
    circ
    0.28
    while
    0.28
    èĢĮåİ»
    0.27
    ãģ§
    0.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.