© 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. 54095
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    çħ§å°Ħ
    -0.28
    grow
    -0.27
    emed
    -0.27
    åı«å£°
    -0.26
    pNet
    -0.26
     stil
    -0.25
    rost
    -0.25
    templ
    -0.24
    interp
    -0.24
    -net
    -0.24
    POSITIVE LOGITS
    uis
    0.28
    bows
    0.28
    zos
    0.25
    heten
    0.24
     acc
    0.24
    ipline
    0.24
    éľŀ
    0.23
    èIJ½ãģ¡
    0.23
     roller
    0.23
    ussion
    0.23
    Activations Density 0.019%

    No Known Activations