© 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. 7821
    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
    æľĿ
    -0.27
     VIC
    -0.26
    _lm
    -0.26
     Nik
    -0.25
     LPC
    -0.25
    uko
    -0.24
    VIC
    -0.24
     Rebel
    -0.24
    endent
    -0.23
    _vi
    -0.23
    POSITIVE LOGITS
    rians
    0.28
    illet
    0.27
    teil
    0.27
    约ä¼ļ
    0.26
     Pett
    0.26
    ramework
    0.25
    apter
    0.25
     sweep
    0.25
    foot
    0.23
    grounds
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.