© 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. 14-TRANSCODER-HP
    7. 39965
    Prev
    Next
    INDEX
    Explanations

    Technical/medical/computer related texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĥĿ
    -0.26
    å¿¿
    -0.25
     Please
    -0.25
    à¸ģร
    -0.25
    ÏĤ
    -0.24
     pragma
    -0.24
    astro
    -0.24
    seek
    -0.24
    yn
    -0.24
     relax
    -0.24
    POSITIVE LOGITS
    plug
    0.34
    åĽŀæĶ¶
    0.29
     accountability
    0.29
    责任ç¼ĸè¾ij
    0.28
    Plug
    0.27
    æ°ª
    0.26
    IFE
    0.25
    izedName
    0.25
    onium
    0.25
    ä¸įæŃ»
    0.25
    Activations Density 0.371%

    No Known Activations