© 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. 9649
    Prev
    Next
    INDEX
    Explanations

    writing content

    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
    cker
    -0.27
    chester
    -0.26
    亲
    -0.26
    æ¼Ĥ
    -0.26
    zend
    -0.25
    åıijå¸ĥ
    -0.25
    çļĦ大
    -0.24
    truck
    -0.24
    enden
    -0.23
    uptools
    -0.23
    POSITIVE LOGITS
    å¥ĹæĪ¿
    0.25
    MARY
    0.24
    æĪĺåľº
    0.23
    屿
    0.23
     taller
    0.23
    女人
    0.23
    媪
    0.23
    groupid
    0.22
     flipped
    0.22
     fact
    0.22
    Activations Density 0.894%

    No Known Activations