© 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. 44253
    Prev
    Next
    INDEX
    Explanations

    technical topics

    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
     flexGrow
    -0.27
    åĮĿ
    -0.25
     distance
    -0.25
     borrowed
    -0.24
     borrow
    -0.24
    ern
    -0.24
     eff
    -0.24
    _DISTANCE
    -0.23
    ously
    -0.23
    ·»
    -0.23
    POSITIVE LOGITS
    鬼
    0.29
    vp
    0.28
    éĺ³åħī
    0.28
     pig
    0.26
    sun
    0.26
     sun
    0.26
    天æ°Ķ
    0.26
    æĪIJå°±
    0.25
    -mon
    0.25
     Chains
    0.25
    Activations Density 0.001%

    No Known Activations