© 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. 29854
    Prev
    Next
    INDEX
    Explanations

    chemical processes

    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
    åĸĩ
    -0.30
    ully
    -0.27
    çĤ¼
    -0.26
    çħī
    -0.24
    绿水
    -0.23
    æİĮ声
    -0.23
    ecret
    -0.23
    é²²
    -0.23
     orig
    -0.23
    (Optional
    -0.23
    POSITIVE LOGITS
    å±ŀ
    0.28
    åı¦ä¸Ģ
    0.26
    ä¸ŃéĹ´
    0.25
    cede
    0.25
    寸
    0.25
    ãĥ»ãĥ»
    0.24
    -holder
    0.24
    好
    0.24
     Layers
    0.24
    ä»ĭ
    0.24
    Activations Density 0.485%

    No Known Activations