© 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. 8157
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    terior
    -0.28
    ä¹Łæĺ¯å¦ĤæѤ
    -0.25
    perm
    -0.25
    ltk
    -0.25
    MAS
    -0.24
    -gun
    -0.24
    ä¸Ģ天
    -0.23
    TY
    -0.23
     Saul
    -0.23
    ТÐķ
    -0.23
    POSITIVE LOGITS
    åĽłæѤ
    0.29
     griev
    0.27
    ви
    0.27
     therefore
    0.26
    usta
    0.26
    istar
    0.26
     effectively
    0.25
    amientos
    0.25
     responsable
    0.24
    mith
    0.24
    Activations Density 0.021%

    No Known Activations