© 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. 9411
    Prev
    Next
    INDEX
    Explanations

    regions

    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
    Negative Logits
    enance
    -0.27
    exion
    -0.27
    иÑĢа
    -0.27
    RetVal
    -0.27
    ernet
    -0.26
    ä¸Ģä¼ļ
    -0.26
    äºĮ代
    -0.26
    yleft
    -0.25
     Sinai
    -0.25
    èħ®
    -0.25
    POSITIVE LOGITS
    Ãģ
    0.32
     заÑĢ
    0.28
    åİĭ
    0.27
    åŁ¹
    0.27
    ype
    0.27
    onda
    0.24
     hy
    0.24
     Ãģ
    0.24
    hya
    0.24
     prze
    0.24
    Activations Density 0.577%

    No Known Activations