© 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. 33-TRANSCODER-HP
    7. 54652
    Prev
    Next
    INDEX
    Explanations

    plant genus / family names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ¡°
    -0.27
    æ³Ħéľ²
    -0.26
    cue
    -0.26
    åĬ¨çĶŁæĪIJ
    -0.26
    zed
    -0.26
    cker
    -0.26
    izi
    -0.26
    æ³Ħæ¼ı
    -0.26
    æİĢ
    -0.25
    ece
    -0.25
    POSITIVE LOGITS
    çķĮ
    0.26
    红线
    0.25
    ç«ĭ
    0.25
     Senate
    0.25
    çĸı
    0.24
    stral
    0.24
     senate
    0.24
     den
    0.24
    landers
    0.24
    åĪĨä¼ļ
    0.24
    Activations Density 0.052%

    No Known Activations