© 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. 8973
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    æĸ¹
    -0.28
     centrally
    -0.26
     ad
    -0.26
     sub
    -0.25
    æĹłåı¯
    -0.24
    éĥ½è¯´
    -0.23
    леж
    -0.23
    atur
    -0.23
    icas
    -0.23
    sub
    -0.23
    POSITIVE LOGITS
    ç²¾é«ĵ
    0.25
    ppy
    0.25
    =forms
    0.25
    AndPassword
    0.25
     counterpart
    0.24
    ên
    0.24
    æł¹æºIJ
    0.24
    åIJĮä¼´
    0.24
    aleza
    0.24
    oused
    0.24
    Activations Density 0.005%

    No Known Activations