© 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. 7299
    Prev
    Next
    INDEX
    Explanations

    Introductions/beginning of articles

    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
     **
    -0.28
    éħ¬
    -0.27
    undra
    -0.26
     ÐŁÐ¾Ð´
    -0.26
    á»ĭa
    -0.25
    HERE
    -0.25
    è¿İ
    -0.24
    ",[
    -0.24
     sed
    -0.24
     period
    -0.24
    POSITIVE LOGITS
    ä¸ī次
    0.30
    inine
    0.28
    kee
    0.25
    enas
    0.24
     getResource
    0.24
    rogen
    0.24
    Rib
    0.24
    _sku
    0.23
    .rar
    0.23
    synthesize
    0.23
    Activations Density 0.033%

    No Known Activations