© 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. 35-TRANSCODER-HP
    7. 40519
    Prev
    Next
    INDEX
    Explanations

    words ending in -ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Living
    -0.42
     Running
    -0.41
     Playing
    -0.38
    è¿IJè¡Į
    -0.37
    running
    -0.37
    驾驶
    -0.36
    living
    -0.36
     living
    -0.35
    Living
    -0.35
    Playing
    -0.34
    POSITIVE LOGITS
     separating
    0.46
     denying
    0.40
     condemning
    0.39
     securing
    0.39
     honoring
    0.38
     dismissing
    0.38
     injuring
    0.38
     suppressing
    0.38
     verifying
    0.37
     fixing
    0.37
    Activations Density 20.140%

    No Known Activations