© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39449
    Prev
    Next
    INDEX
    Explanations

    technical writing/code

    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
    Negative Logits
    stein
    -0.28
    endir
    -0.26
    liner
    -0.26
    Collapse
    -0.25
    inalg
    -0.24
    ê²IJ
    -0.24
    cline
    -0.24
    ãĥ«ãĥ¼
    -0.24
    æĿ¥è¯´
    -0.24
    ç´łè´¨æķĻèĤ²
    -0.24
    POSITIVE LOGITS
    çĴ
    0.27
    ä»ĸ们ä¼ļ
    0.26
    ħ§
    0.26
    çŁ³æ²¹
    0.26
    è¤
    0.25
    sun
    0.25
    pire
    0.25
    åºĬä½į
    0.25
     iconName
    0.24
    ä»ĸä¼ļ
    0.24
    Activations Density 0.162%

    No Known Activations