© 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. 9548
    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
    Negative Logits
    leep
    -0.28
    =edge
    -0.25
    ä¾
    -0.25
    åģ¥åº·åıijå±ķ
    -0.23
    MAND
    -0.23
     designed
    -0.23
    мол
    -0.23
    å²ŃåįĹ
    -0.23
    anan
    -0.22
     intended
    -0.22
    POSITIVE LOGITS
    /contact
    0.27
    haps
    0.26
    ä¸Ģèĩ´
    0.26
    åĪĴ
    0.25
    ä¸ŃéĹ´
    0.25
     Levels
    0.25
    lotte
    0.24
     Clearance
    0.24
    /current
    0.24
    \Field
    0.24
    Activations Density 0.051%

    No Known Activations

    This feature has no known activations.