© 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. 54582
    Prev
    Next
    INDEX
    Explanations

    research journals and academic studies

    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
    èĩªçĦ¶ç§ijåѦ
    -0.28
    çīĩåĪ»
    -0.27
    .eu
    -0.26
     Current
    -0.26
     Trial
    -0.25
     Interior
    -0.25
     Science
    -0.25
    radi
    -0.25
     con
    -0.25
     trial
    -0.25
    POSITIVE LOGITS
    oleon
    0.28
     пÑĢÑı
    0.25
     pee
    0.25
    èŀį
    0.25
    åĨķ
    0.24
    stitutions
    0.24
    订
    0.24
     Sears
    0.23
    ocalypse
    0.23
    ç¡ķ
    0.23
    Activations Density 0.008%

    No Known Activations