© 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. 12-TRANSCODER-HP
    7. 23479
    Prev
    Next
    INDEX
    Explanations

    publishing, legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inqu
    -0.26
    -lined
    -0.26
    è¢ĸ
    -0.25
    ä¸ĢæµģçļĦ
    -0.25
    eam
    -0.25
    oga
    -0.25
    extField
    -0.25
     Rounds
    -0.25
    梦è§ģ
    -0.25
    请çĤ¹åĩ»
    -0.25
    POSITIVE LOGITS
    å®£ä¼ł
    0.29
     Dissertation
    0.27
     publicly
    0.26
    仲
    0.26
    æĸ°éĹ»
    0.26
    ä¼łæĴŃ
    0.26
    åĩºçīĪ
    0.25
     δ
    0.25
    blogs
    0.25
    iral
    0.25
    Activations Density 0.001%

    No Known Activations