© 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. 9363
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¿ĺ以为
    -0.25
    ç«ŁçĦ¶
    -0.24
     electronically
    -0.24
    ä¹Łåıªèĥ½
    -0.24
     privileged
    -0.24
    ÙģÙĪ
    -0.24
    ä½ŀ
    -0.23
    ervice
    -0.23
    èĻ«
    -0.23
     ux
    -0.23
    POSITIVE LOGITS
    راÙħ
    0.28
    äh
    0.25
    çĽĺ
    0.25
    ahoma
    0.25
     Aim
    0.24
    -conf
    0.24
    æł¸å¿ĥ
    0.23
     Kear
    0.23
    缤
    0.23
    irement
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.