© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7639
    Prev
    Next
    INDEX
    Explanations

    programming code/licenses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    太æŀģ
    -0.27
    æIJŃæ¡£
    -0.27
     nominated
    -0.26
     duo
    -0.24
     balance
    -0.24
     deed
    -0.24
    工人
    -0.24
    ernes
    -0.24
    edo
    -0.24
    .pivot
    -0.23
    POSITIVE LOGITS
    ceed
    0.28
    obot
    0.27
    vis
    0.25
     rhe
    0.25
    oru
    0.24
    åı¯è§ģ
    0.23
     Vis
    0.23
    æ´±
    0.23
    lob
    0.23
     Scholars
    0.23
    Activations Density 0.009%

    No Known Activations