© 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. 9322
    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
    ary
    -0.30
    angers
    -0.27
    ions
    -0.27
    ç´¯äºĨ
    -0.26
    ä¹Łä¸įè¦ģ
    -0.26
    ational
    -0.26
    istes
    -0.24
    æ¯Ĥ
    -0.24
    iner
    -0.24
    inal
    -0.23
    POSITIVE LOGITS
    INCLUDED
    0.27
     crowds
    0.25
    _True
    0.25
    åı·çłģ
    0.25
    ecz
    0.25
    еÑģÑĤÑĮ
    0.24
    EMS
    0.23
     ect
    0.23
    Media
    0.22
    ECT
    0.22
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.