© 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. 8749
    Prev
    Next
    INDEX
    Explanations

    bat

    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
    phoon
    -0.28
    etti
    -0.27
    PageIndex
    -0.26
     Isles
    -0.26
    cente
    -0.25
    导读
    -0.25
    ugal
    -0.25
    §
    -0.25
    åºŃ
    -0.24
    ç½ijåıĭè¯Ħ论
    -0.24
    POSITIVE LOGITS
    ä¸ĭåįĬ
    0.26
      	↵
    0.25
     whip
    0.24
    èĮ¹
    0.23
    çĭŃ
    0.23
     mouth
    0.23
     Edgar
    0.23
    ctors
    0.23
     vastly
    0.23
     aside
    0.22
    Activations Density 1.090%

    No Known Activations