© 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. 19-TRANSCODER-HP
    7. 8523
    Prev
    Next
    INDEX
    Explanations

    Radiology

    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
    IFIC
    -0.28
    oir
    -0.28
    edith
    -0.27
    quate
    -0.25
    ãĥĥãĥĪ
    -0.25
    غÙĨÙĬ
    -0.25
    igu
    -0.24
    epend
    -0.24
    çĨ¨
    -0.24
    kan
    -0.24
    POSITIVE LOGITS
     census
    0.30
    çĽijäºĭä¼ļ
    0.28
     Census
    0.26
    æīĵ好
    0.25
     firing
    0.25
    çłĶ究æĬ¥åijĬ
    0.24
    /archive
    0.24
    	mock
    0.23
    è¿Ļä¹Ī说
    0.23
    Disallow
    0.23
    Activations Density 0.909%

    No Known Activations