© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7342
    Prev
    Next
    INDEX
    Explanations

    with

    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
    icut
    -0.26
     boycott
    -0.26
    é¢ł
    -0.25
    -parse
    -0.25
    ishop
    -0.25
     indoors
    -0.24
     darn
    -0.24
    /filter
    -0.24
     arrogant
    -0.24
    ặ
    -0.23
    POSITIVE LOGITS
    ç»ıéªĮåĢ¼
    0.28
    chos
    0.28
    omi
    0.26
     pname
    0.25
    æĭ¬
    0.25
    éĥ½ä¸įä¼ļ
    0.25
    åĪĨä¼ļ
    0.24
    æŁĶæĢ§
    0.24
    åIJįä¹ī
    0.24
    ä¹Łä¸įèĥ½
    0.24
    Activations Density 0.024%

    No Known Activations