© 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. 19-TRANSCODER-HP
    7. 9434
    Prev
    Next
    INDEX
    Explanations

    Citations with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è±ģ
    -0.41
    åıªéľĢè¦ģ
    -0.40
    åıªéľĢ
    -0.39
    æĹłéľĢ
    -0.38
    ä¸įéľĢè¦ģ
    -0.36
    åıªè¦ģ
    -0.34
    ä¸įçĶ¨æĭħå¿ĥ
    -0.32
    åıªè¦ģæľī
    -0.31
    åıªè¦ģä½ł
    -0.30
     ins
    -0.30
    POSITIVE LOGITS
    æĭĴç»Ŀ
    0.31
    tere
    0.28
     못
    0.28
    æĭĴçµķ
    0.28
    严
    0.28
    åıį对
    0.28
    .Fail
    0.27
    æĭĴä¸į
    0.27
    ä¸įèĥ½åĨį
    0.27
    åļ´
    0.26
    Activations Density 0.002%

    No Known Activations