© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9384
    Prev
    Next
    INDEX
    Explanations

    This

    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
    ç½ļ
    -0.28
    uvre
    -0.28
    æĭ¦
    -0.26
     ming
    -0.26
    uba
    -0.26
    wig
    -0.25
    ган
    -0.25
    å±ģ
    -0.25
     applicable
    -0.25
    /ws
    -0.25
    POSITIVE LOGITS
    æĦı
    0.29
    /weather
    0.28
    ""↵
    0.26
     elgg
    0.25
    stown
    0.25
     getLogger
    0.25
     nl
    0.25
    顺çĿĢ
    0.24
    olt
    0.24
    nl
    0.24
    Activations Density 0.005%

    No Known Activations