© 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. 44050
    Prev
    Next
    INDEX
    Explanations

    electrical current/voltage

    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
    enser
    -0.29
    çŀŃ
    -0.27
    ادÙĬØ©
    -0.25
     Normal
    -0.25
    PLAIN
    -0.25
    enses
    -0.25
    ä¿®
    -0.25
    neau
    -0.24
    arning
    -0.24
    çĽĺ
    -0.24
    POSITIVE LOGITS
     levels
    0.28
    éĤ®ä»¶
    0.27
    uffle
    0.27
    ãĤ¸ãĤ§
    0.27
    èµ·ãģį
    0.26
     level
    0.25
    ফ
    0.25
    -inverse
    0.24
    Pen
    0.24
     recipro
    0.24
    Activations Density 0.003%

    No Known Activations