© 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. 8700
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    åĪĽç«ĭ
    -0.28
     profiler
    -0.28
     prof
    -0.27
    亮
    -0.27
     comforts
    -0.27
     pari
    -0.26
     convinc
    -0.25
    è´¿èµĤ
    -0.25
     riches
    -0.25
    辩论
    -0.24
    POSITIVE LOGITS
    isel
    0.31
    俯
    0.29
    .inc
    0.29
    -inc
    0.28
    odem
    0.28
     Ninth
    0.27
    éĤ£éĩĮ
    0.27
    Ñģан
    0.26
    quot
    0.26
    andler
    0.25
    Activations Density 0.031%

    No Known Activations