© 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. 9-TRANSCODER-HP
    7. 29951
    Prev
    Next
    INDEX
    Explanations

    years or age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨĽäºº
    -0.31
     borderWidth
    -0.28
     Affero
    -0.25
    åħ±åIJĮåĬªåĬĽ
    -0.23
    ä»ĸèĩªå·±
    -0.23
    fers
    -0.23
    æľĪ以æĿ¥
    -0.23
     cuckold
    -0.23
    çĥĤ
    -0.23
    ucz
    -0.23
    POSITIVE LOGITS
     Ide
    0.27
    年代
    0.27
    cene
    0.27
    åł´
    0.26
     Rhodes
    0.26
    Ide
    0.26
     pattern
    0.25
     por
    0.25
    indr
    0.25
    çĨĺ
    0.24
    Activations Density 8.704%

    No Known Activations