© 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. 52730
    Prev
    Next
    INDEX
    Explanations

    Anatomy/medicine texts

    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
    jni
    -0.33
    个çĻ¾åĪĨ
    -0.29
    èĤ²
    -0.28
    -cookie
    -0.27
    udeau
    -0.27
    quila
    -0.27
    pe
    -0.26
    uously
    -0.26
    _pe
    -0.26
    ertainment
    -0.25
    POSITIVE LOGITS
    åīį
    0.39
     fwd
    0.31
     front
    0.31
    Front
    0.30
    åīįåIJİ
    0.30
    front
    0.30
    åīįæĸ¹
    0.29
    _front
    0.29
     anterior
    0.29
     prefixes
    0.29
    Activations Density 0.027%

    No Known Activations