© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53051
    Prev
    Next
    INDEX
    Explanations

    Medical contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     marker
    -0.28
    .mo
    -0.28
    idx
    -0.27
    IU
    -0.27
     aff
    -0.27
    inta
    -0.26
    CCI
    -0.26
    ç´¢
    -0.26
    lyn
    -0.26
     i
    -0.25
    POSITIVE LOGITS
    dic
    0.30
    imations
    0.29
    dra
    0.29
     dic
    0.28
    etic
    0.27
    dition
    0.27
    åī½
    0.27
    contr
    0.26
     opposite
    0.26
    缸åıį
    0.26
    Activations Density 0.010%

    No Known Activations