© 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. 41174
    Prev
    Next
    INDEX
    Explanations

    Academic excerpts

    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
     Ske
    -0.21
    æŃ¹
    -0.20
    iaux
    -0.19
    åĩºå·®
    -0.19
    éħ¥
    -0.18
    į°
    -0.18
    edException
    -0.18
    ÑĮÑıн
    -0.18
     blessed
    -0.18
    ãĤŃãĥ£ãĥ³
    -0.17
    POSITIVE LOGITS
    æľīä¸Ģ天
    0.20
    çĶµåĻ¨
    0.20
    çľĭçĿĢ
    0.17
    åĨħç½®
    0.17
    æľīä¸Ģ次
    0.17
     Yoshi
    0.17
    erras
    0.17
    æıĨ
    0.17
    è¿ľæĻ¯
    0.17
    åıĸ
    0.17
    Activations Density 6.739%

    No Known Activations