© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7974
    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
    åıŃ
    -0.28
     mot
    -0.27
     ATK
    -0.27
     tour
    -0.26
     Cycl
    -0.25
    ecret
    -0.25
    _pins
    -0.24
    andas
    -0.24
    _LVL
    -0.23
     ê·¸ëłĩì§Ģ
    -0.23
    POSITIVE LOGITS
    AndView
    0.28
    å¤ľ
    0.26
    ابة
    0.25
     apprentice
    0.25
    structured
    0.25
    reveal
    0.25
    .testing
    0.25
    testing
    0.25
    orf
    0.24
    ä¼°ç®Ĺ
    0.24
    Activations Density 0.138%

    No Known Activations

    This feature has no known activations.