© 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. 54287
    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
     Care
    -0.29
    çİ©
    -0.25
    .rf
    -0.25
     threaded
    -0.25
    ksi
    -0.25
     land
    -0.24
     plant
    -0.24
     dig
    -0.24
    .pipe
    -0.24
    Care
    -0.24
    POSITIVE LOGITS
    amt
    0.32
    fos
    0.28
    oge
    0.28
    åĢ¦
    0.27
    dden
    0.27
    fat
    0.27
    assa
    0.26
    ething
    0.26
    yne
    0.26
    çĸ²
    0.26
    Activations Density 0.011%

    No Known Activations