© 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. 8390
    Prev
    Next
    INDEX
    Explanations

    Alcohol

    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
    unge
    -0.31
    æ³ķå¾ĭ责任
    -0.26
    éŨåīį
    -0.26
    æľīè¿Ļæł·çļĦ
    -0.25
     causa
    -0.24
    affer
    -0.24
    iards
    -0.23
    TextView
    -0.23
     strengthened
    -0.23
    Ingredients
    -0.23
    POSITIVE LOGITS
    gers
    0.27
    embr
    0.26
    relative
    0.26
    sen
    0.25
     external
    0.25
    cape
    0.24
    nown
    0.24
    ä¸įå°½
    0.24
     Gór
    0.24
    semble
    0.24
    Activations Density 0.004%

    No Known Activations