© 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. 8549
    Prev
    Next
    INDEX
    Explanations

    Subtraction/difference

    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
    &o
    -0.28
     buttonText
    -0.27
    ãģ¡ãĤī
    -0.26
    åĽł
    -0.25
    èģĶ缣
    -0.24
     frag
    -0.24
    flows
    -0.24
    mag
    -0.24
    åĺĢ
    -0.24
    èĢĹ
    -0.24
    POSITIVE LOGITS
    åħ¨å¹´
    0.29
     emperor
    0.28
    .original
    0.27
     classics
    0.27
    eree
    0.26
     Monterey
    0.25
    	finally
    0.25
     Universe
    0.25
    -mount
    0.24
    /watch
    0.24
    Activations Density 0.027%

    No Known Activations