© 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. 7633
    Prev
    Next
    INDEX
    Explanations

    mixed, extracted text snippets

    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
     span
    -0.27
    otte
    -0.27
     batt
    -0.25
    agit
    -0.24
    éģĤ
    -0.24
    eki
    -0.24
     nano
    -0.24
    (span
    -0.24
    å¾Ģåīį
    -0.24
    leveland
    -0.23
    POSITIVE LOGITS
    ä¸ŀ
    0.27
    ä¸į管
    0.26
    ä¸įç®¡ä½ł
    0.26
    ony
    0.26
     succès
    0.25
    é£İéĻ©
    0.24
    Except
    0.24
    roots
    0.24
     Root
    0.23
     sole
    0.23
    Activations Density 0.001%

    No Known Activations