© 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. 54537
    Prev
    Next
    INDEX
    Explanations

    Medical procedures

    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
    ry
    -0.31
    ep
    -0.28
     sund
    -0.27
    pm
    -0.26
    rica
    -0.26
    err
    -0.26
    ries
    -0.25
    cpt
    -0.25
     intr
    -0.25
    ocracy
    -0.25
    POSITIVE LOGITS
    agram
    0.31
    afi
    0.27
    èĬ½
    0.26
    ady
    0.26
    ðŁĵĪ
    0.26
    -reference
    0.25
     ControllerBase
    0.25
     strokeWidth
    0.25
    ads
    0.24
    avn
    0.24
    Activations Density 0.031%

    No Known Activations