© 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. 31-TRANSCODER-HP
    7. 19770
    Prev
    Next
    INDEX
    Explanations

    movement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĢļ
    -0.29
     fread
    -0.28
    å®ŀä½ĵ
    -0.27
    itel
    -0.26
     Paginator
    -0.25
    ",(
    -0.25
     doch
    -0.25
     espos
    -0.24
    ç»Ħ
    -0.24
     Tart
    -0.24
    POSITIVE LOGITS
     movement
    0.54
     movements
    0.48
     Movement
    0.47
    movement
    0.44
    Movement
    0.42
    push
    0.41
     push
    0.41
     Mov
    0.40
     Push
    0.39
    Mov
    0.39
    Activations Density 0.137%

    No Known Activations