© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107026
    Prev
    Next
    INDEX
    Explanations

    assignment operators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä»»ä½ķæŶåĢĻ
    -0.25
    '||
    -0.24
    .backends
    -0.24
     onward
    -0.24
    .FileNotFoundException
    -0.24
    缮åħī
    -0.23
    ä¸ĢåĪ»
    -0.23
    -Benz
    -0.23
    NDER
    -0.22
     lẫn
    -0.22
    POSITIVE LOGITS
    =
    0.60
    ="
    0.56
    ='
    0.56
    ={'
    0.52
    =(
    0.50
    =self
    0.50
    ={"
    0.48
    =[
    0.48
    =False
    0.47
    ={
    0.46
    Activations Density 1.494%

    No Known Activations