© 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. 107166
    Prev
    Next
    INDEX
    Explanations

    disparity/parity

    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
    initely
    -0.29
    ents
    -0.28
    elman
    -0.26
    ercial
    -0.26
    uding
    -0.25
     nors
    -0.25
    egers
    -0.25
     outpatient
    -0.25
     eslint
    -0.25
    compiled
    -0.25
    POSITIVE LOGITS
    -bal
    0.28
    son
    0.28
    v
    0.27
    ãģļãģ£ãģ¨
    0.25
    so
    0.25
    vel
    0.25
     beauty
    0.25
    vo
    0.24
     board
    0.24
     vision
    0.24
    Activations Density 1.103%

    No Known Activations