© 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. 18271
    Prev
    Next
    INDEX
    Explanations

    technical/programming document

    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
    .setColumns
    -0.27
    bow
    -0.26
    enson
    -0.25
    ulet
    -0.25
    éĽ
    -0.25
    æĥł
    -0.25
    æĸ½
    -0.24
    è¿ľæ´ĭ
    -0.24
    uja
    -0.24
    ä¼ļä¸Ĭ
    -0.24
    POSITIVE LOGITS
    GPL
    0.28
    è£ħç½®
    0.27
    MG
    0.27
    imed
    0.26
    åħīçĶµ
    0.26
     lic
    0.25
    -ground
    0.24
    rig
    0.24
     Found
    0.24
    found
    0.24
    Activations Density 1.793%

    No Known Activations