© 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. 8493
    Prev
    Next
    INDEX
    Explanations

    restriction

    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
    adin
    -0.28
    åŁİåİ¿
    -0.27
    çĦ¡æ³ķ
    -0.26
    累累
    -0.25
    æĦıæĥ³ä¸įåĪ°
    -0.24
    pole
    -0.24
    çļĦéĩį大
    -0.24
    umper
    -0.24
    äºĭ實
    -0.24
     badges
    -0.24
    POSITIVE LOGITS
    \
    0.27
    令
    0.27
    enn
    0.26
    Æ°
    0.26
    ni
    0.26
     Pin
    0.24
    æ´Ĺ
    0.24
     pin
    0.24
    ç²³
    0.24
    g
    0.24
    Activations Density 0.083%

    No Known Activations