© 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. 54617
    Prev
    Next
    INDEX
    Explanations

    scientific/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
    Negative Logits
     Classes
    -0.33
     shadows
    -0.31
     Blades
    -0.30
    Classes
    -0.30
     classes
    -0.29
     negatives
    -0.28
    ammers
    -0.27
     Shadows
    -0.27
     Rays
    -0.27
    classes
    -0.27
    POSITIVE LOGITS
     systems
    0.39
     Systems
    0.35
    systems
    0.33
    Systems
    0.28
    ystems
    0.28
     tr
    0.27
    è¾¹
    0.27
    éĤ¸
    0.26
    oped
    0.26
    çĥŃæIJľ
    0.26
    Activations Density 0.004%

    No Known Activations