© 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. 9497
    Prev
    Next
    INDEX
    Explanations

    current time

    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
     CALLBACK
    -0.28
     unrelated
    -0.27
    å¤Ķ
    -0.26
    ãģĦãģĭ
    -0.26
     elkaar
    -0.25
     punches
    -0.24
    åħ¶ä»ĸçļĦ
    -0.24
     mbox
    -0.24
    ',čč↵
    -0.24
    regor
    -0.23
    POSITIVE LOGITS
     currently
    0.54
    缮åīį
    0.51
    æѤåĪ»
    0.45
    currently
    0.45
    å½ĵåīį
    0.44
     Currently
    0.43
     presently
    0.41
    Currently
    0.41
     current
    0.40
    çİ°éĺ¶æ®µ
    0.40
    Activations Density 0.636%

    No Known Activations