© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9672
    Prev
    Next
    INDEX
    Explanations

    Brun

    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
    Negative Logits
    éĹ»
    -0.28
    /pm
    -0.27
    pub
    -0.27
    programs
    -0.26
     pm
    -0.26
    pm
    -0.25
    _SIDE
    -0.24
    sendMessage
    -0.24
    åıij
    -0.24
     lif
    -0.23
    POSITIVE LOGITS
    é³Ħ
    0.31
    anka
    0.25
     chick
    0.24
    ama
    0.24
     condensed
    0.24
    éĽĨåľĺ
    0.24
    交æĺĵå¹³åı°
    0.24
    åĥĩ
    0.23
    èīº
    0.23
    amous
    0.23
    Activations Density 0.008%

    No Known Activations