© 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. 44224
    Prev
    Next
    INDEX
    Explanations

    political/legal discussions

    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
    iping
    -0.30
    inger
    -0.30
    INGER
    -0.28
    rape
    -0.28
    abeth
    -0.27
    ModelError
    -0.26
    ilage
    -0.25
    åŀĨ
    -0.24
    纪
    -0.24
    udas
    -0.24
    POSITIVE LOGITS
    åĭĥ
    0.29
    大åıij
    0.28
    esis
    0.27
    fa
    0.26
    _fa
    0.26
    aac
    0.25
    bps
    0.25
     sal
    0.24
     elev
    0.24
    atron
    0.24
    Activations Density 0.007%

    No Known Activations