© 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. 32-TRANSCODER-HP
    7. 41051
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    0
    -0.40
    bis
    -0.30
    5
    -0.28
    éªĨ
    -0.26
    çĶ³
    -0.26
     obst
    -0.25
    rd
    -0.25
    website
    -0.24
    swift
    -0.24
    A
    -0.24
    POSITIVE LOGITS
     distance
    0.32
     pounds
    0.31
     miles
    0.30
     inches
    0.30
    ç§ijæĬĢèĤ¡ä»½
    0.29
    itol
    0.29
     kilometers
    0.28
    ottes
    0.28
    utes
    0.28
     kilometres
    0.28
    Activations Density 0.007%

    No Known Activations