© 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. 6150
    Prev
    Next
    INDEX
    Explanations

    Free food/lunch programs

    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
     Nights
    -0.27
     nights
    -0.27
    woods
    -0.26
    ataire
    -0.25
    tures
    -0.25
    erville
    -0.24
    avy
    -0.23
    ENDER
    -0.23
    rides
    -0.23
    neys
    -0.23
    POSITIVE LOGITS
    âĶĮ
    0.27
    æĪij说
    0.26
    æĪijä¼ļ
    0.25
    åķ¬
    0.25
    unct
    0.25
    æ®Ħ
    0.25
     Tang
    0.24
    UNCT
    0.24
    åħį责声æĺİ
    0.24
    âĦħ
    0.24
    Activations Density 0.007%

    No Known Activations