© 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. 4-TRANSCODER-HP
    7. 27
    Prev
    Next
    INDEX
    Explanations

    icy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zia
    -0.26
    ä¸¤å¼ł
    -0.26
    bia
    -0.26
    åĩłå¼ł
    -0.25
    arkin
    -0.23
    appen
    -0.23
    /***/
    -0.23
    udes
    -0.23
    ĺ认
    -0.23
    ainty
    -0.23
    POSITIVE LOGITS
    eur
    0.32
     East
    0.26
    ging
    0.26
    croll
    0.25
    ing
    0.24
    roups
    0.24
    åħ»
    0.24
     overflowing
    0.24
    cio
    0.24
     exhaustive
    0.23
    Activations Density 0.011%

    No Known Activations