© 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. 4753
    Prev
    Next
    INDEX
    Explanations

    News articles and stories

    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
    åĽ¢è´Ń
    -0.25
    -Sah
    -0.24
    ilst
    -0.24
    stral
    -0.24
     rendition
    -0.24
     Stateless
    -0.24
    fact
    -0.23
    à¸ĺ
    -0.23
    -UA
    -0.23
    çŀ³
    -0.23
    POSITIVE LOGITS
    bose
    0.29
    #elif
    0.28
    åĵªä¸Ģ个
    0.26
    å¾Ģå¤ĸ
    0.25
    imu
    0.24
    ä¹ı
    0.24
    å¾Ģ
    0.24
    iva
    0.23
    );;↵
    0.23
    è¾¹
    0.23
    Activations Density 0.080%

    No Known Activations