© 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. 7308
    Prev
    Next
    INDEX
    Explanations

    math, code

    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
    æ»ļ
    -0.26
    æ»ļåĬ¨
    -0.25
    Ĥæķ°
    -0.25
    inka
    -0.24
    oya
    -0.24
    é¢ĺ缮
    -0.24
     inf
    -0.24
    ramid
    -0.23
    tsy
    -0.23
    å¹³æĿ¿
    -0.23
    POSITIVE LOGITS
    vig
    0.27
    ÑĦоÑĢ
    0.25
     strength
    0.25
    ion
    0.25
    é¡
    0.24
     pud
    0.24
    strength
    0.23
     Vig
    0.23
    zure
    0.23
    aton
    0.23
    Activations Density 0.003%

    No Known Activations