© 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. 7263
    Prev
    Next
    INDEX
    Explanations

    importance

    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
    sparse
    -0.29
    gression
    -0.27
    åĽłåľ°
    -0.26
     ende
    -0.26
    åģļä¸ĢäºĽ
    -0.25
    PEED
    -0.24
    erge
    -0.24
     sparse
    -0.24
    _tim
    -0.23
    iesen
    -0.23
    POSITIVE LOGITS
    ä¸ĭåįĬ
    0.27
    LS
    0.26
    -or
    0.25
    åī¯æĢ»
    0.25
    _contin
    0.24
    é¢ľ
    0.24
    交æİ¥
    0.24
    boards
    0.24
     PRIMARY
    0.24
     Lah
    0.24
    Activations Density 0.066%

    No Known Activations