© 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. 9061
    Prev
    Next
    INDEX
    Explanations

    Cause and effect

    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
     muj
    -0.29
     institution
    -0.27
    ç§ijæĬĢèĤ¡ä»½
    -0.27
    å®Įç¾İ
    -0.26
    xing
    -0.26
    zyst
    -0.26
    maj
    -0.26
     Rif
    -0.26
    htag
    -0.25
    å®Įç¾İçļĦ
    -0.25
    POSITIVE LOGITS
    iles
    0.26
     воз
    0.26
    alan
    0.26
    試
    0.25
     formatter
    0.25
     die
    0.25
    Case
    0.25
    é£ŀ
    0.25
    éħµ
    0.25
     entitled
    0.25
    Activations Density 0.007%

    No Known Activations