© 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. 30-TRANSCODER-HP
    7. 97128
    Prev
    Next
    INDEX
    Explanations

    say medical terminology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĤĢ
    -0.29
    idis
    -0.28
    Identity
    -0.26
    um
    -0.26
     getElement
    -0.26
    表达
    -0.25
    iddy
    -0.25
    使ä¹ĭ
    -0.25
    unga
    -0.25
    _identity
    -0.24
    POSITIVE LOGITS
    oods
    0.27
    lobs
    0.26
     pains
    0.26
    çĭ
    0.26
    бил
    0.25
    è¿ĩ
    0.25
    irror
    0.25
    ç»ĨåĪĻ
    0.25
     exercises
    0.25
     viruses
    0.24
    Activations Density 0.904%

    No Known Activations