© 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. 24-TRANSCODER-HP
    7. 150541
    Prev
    Next
    INDEX
    Explanations

    people and relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çľĭä¸įåĩº
    -0.27
    raham
    -0.26
    ODY
    -0.26
    åŃĢ
    -0.25
    ycz
    -0.24
     Unified
    -0.24
    <AM
    -0.24
    æīİæł¹
    -0.24
    ãĥ¡ãĥ¼ãĤ«ãĥ¼
    -0.23
     Pty
    -0.23
    POSITIVE LOGITS
    åı¯ä¾Ľ
    0.32
     accessible
    0.32
    ä¼ļ被
    0.31
    被è§Ĩ为
    0.30
     playable
    0.30
     eaten
    0.30
     achievable
    0.29
     perceived
    0.29
    ä¾Ľ
    0.29
     avoided
    0.29
    Activations Density 0.944%

    No Known Activations