© 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. 53673
    Prev
    Next
    INDEX
    Explanations

    stration

    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
    ä¸įå°½
    -0.28
    å¿į
    -0.28
    缺éĻ·
    -0.26
    tre
    -0.26
    kest
    -0.24
    æĭĸ
    -0.24
    éĺĸ
    -0.24
     absorb
    -0.24
    å®Ľ
    -0.24
    ç²īå°ĺ
    -0.24
    POSITIVE LOGITS
    arus
    0.28
     ensured
    0.26
     topped
    0.26
     billionaire
    0.25
    ellar
    0.25
    è£ħ
    0.25
     bills
    0.24
     surfaces
    0.24
     Pascal
    0.24
     setTimeout
    0.23
    Activations Density 0.028%

    No Known Activations