© 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. 9-TRANSCODER-HP
    7. 29147
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Probe
    -0.27
    oire
    -0.27
    opr
    -0.26
    ,eg
    -0.24
    ror
    -0.24
    не
    -0.23
    bara
    -0.23
    ä½İ温
    -0.23
    Probe
    -0.23
     probes
    -0.22
    POSITIVE LOGITS
    lah
    0.26
    ç»ı纪人
    0.26
    æī¹
    0.25
     bound
    0.24
     MVP
    0.24
    Bound
    0.24
     bonded
    0.24
     skeleton
    0.24
    æĬ¥åIJį
    0.23
    MLS
    0.23
    Activations Density 0.970%

    No Known Activations