© 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. 19105
    Prev
    Next
    INDEX
    Explanations

    N

    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
     natural
    -0.27
     principal
    -0.26
    natural
    -0.26
     tables
    -0.26
    çIJ¢ç£¨
    -0.25
    VA
    -0.25
    edd
    -0.25
    -script
    -0.25
     flesh
    -0.25
    moth
    -0.25
    POSITIVE LOGITS
    å´ĩ
    0.27
    ssp
    0.27
    .stamp
    0.27
    boro
    0.26
    太
    0.26
    stery
    0.26
    å¼ĭ
    0.26
    onen
    0.25
    _drawer
    0.25
    太快
    0.25
    Activations Density 0.001%

    No Known Activations