© 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. 40830
    Prev
    Next
    INDEX
    Explanations

    4

    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
    emarks
    -0.31
    ROOM
    -0.29
    .enqueue
    -0.29
    rons
    -0.27
    amodel
    -0.27
    Mounted
    -0.26
    elight
    -0.26
    romo
    -0.26
    reste
    -0.26
    -ROM
    -0.25
    POSITIVE LOGITS
    z
    0.31
    éģį
    0.30
    严
    0.29
     aspect
    0.28
    æŁ³
    0.28
    Default
    0.27
    æĿ¾
    0.27
    念
    0.26
    za
    0.26
    C
    0.26
    Activations Density 0.001%

    No Known Activations