© 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. 53123
    Prev
    Next
    INDEX
    Explanations

    blog posts and articles

    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
    .feature
    -0.27
     feature
    -0.27
    Govern
    -0.26
    umann
    -0.26
    KEN
    -0.25
    енно
    -0.25
     budgets
    -0.24
    mat
    -0.24
    ken
    -0.24
    ếm
    -0.24
    POSITIVE LOGITS
     Places
    0.28
     sounds
    0.28
     Forces
    0.27
     Causes
    0.26
    sounds
    0.26
     Results
    0.26
    (Resources
    0.25
     Questions
    0.25
     parallels
    0.25
     Takes
    0.25
    Activations Density 0.118%

    No Known Activations