© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4887
    Prev
    Next
    INDEX
    Explanations

    Environmental / location conditions

    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
    é£İåIJ¹
    -0.31
     tod
    -0.25
     tern
    -0.24
    afa
    -0.24
    Attribute
    -0.24
     notes
    -0.24
    å§ijå¨ĺ
    -0.23
    游æĪıè£ħå¤ĩ
    -0.23
    é²ľèĬ±
    -0.23
    Propagation
    -0.23
    POSITIVE LOGITS
    illion
    0.27
    lege
    0.25
    大çĽĺ
    0.25
    onis
    0.25
     absl
    0.24
    迷失
    0.24
    éĩıåĮĸ
    0.24
     LEG
    0.24
    LEG
    0.23
    ä¸ĩåIJį
    0.23
    Activations Density 0.833%

    No Known Activations