© 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. 31-TRANSCODER-HP
    7. 18745
    Prev
    Next
    INDEX
    Explanations

    computer code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setters
    -0.27
    çĬĩ
    -0.27
     mug
    -0.26
    -many
    -0.25
    -days
    -0.25
    å¾Īæĥ³
    -0.25
    -exclusive
    -0.25
     PROVID
    -0.24
     popped
    -0.24
    Quiet
    -0.24
    POSITIVE LOGITS
    onym
    0.28
    uta
    0.28
    am
    0.27
    åĮĸ
    0.26
    m
    0.25
    £
    0.25
    éĸĵ
    0.25
    iss
    0.25
    CT
    0.24
    éĹ´
    0.24
    Activations Density 0.005%

    No Known Activations