© 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. 30-TRANSCODER-HP
    7. 96166
    Prev
    Next
    INDEX
    Explanations

    Programming/code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    encies
    -0.30
    ives
    -0.28
     action
    -0.28
    容å¿į
    -0.25
    äºĭ件
    -0.25
    åľºä¸Ĭ
    -0.25
    ä½łåºĶ该
    -0.25
     Monsters
    -0.24
    IZES
    -0.24
    action
    -0.23
    POSITIVE LOGITS
    è¯Ŀ
    0.28
     Eag
    0.26
    天天
    0.25
    çīĻ
    0.25
    orest
    0.24
    keyboard
    0.24
    getExtension
    0.24
    éĶ®çĽĺ
    0.24
    .reason
    0.24
    oman
    0.23
    Activations Density 0.100%

    No Known Activations