© 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. 4784
    Prev
    Next
    INDEX
    Explanations

    names

    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
    /install
    -0.28
    !--
    -0.27
    ä½ľåĩºäºĨ
    -0.26
    afa
    -0.26
    arkin
    -0.25
    ä¸Ģè¶Ł
    -0.25
     innocence
    -0.25
     morale
    -0.25
    fav
    -0.25
    åĽĽä¸ªæĦıè¯Ĩ
    -0.24
    POSITIVE LOGITS
     Topic
    0.30
    ãĤīãģĦ
    0.28
    .topic
    0.27
    è¡·
    0.27
     ÙħÙĪضÙĪع
    0.27
    íķ´ìĦľ
    0.25
    Ä±ÅŁÄ±
    0.25
     Topics
    0.25
    SIGN
    0.25
    .Topic
    0.24
    Activations Density 0.069%

    No Known Activations