© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7343
    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
    +":
    -0.28
    ä¿¡ä»»
    -0.28
    Trust
    -0.27
     trust
    -0.27
    æĹłéĻIJ
    -0.26
    _NR
    -0.25
     Trust
    -0.25
    (clone
    -0.25
     hop
    -0.24
    .clone
    -0.24
    POSITIVE LOGITS
    åħ¨çº¿
    0.27
    ninger
    0.26
     bridges
    0.26
    çĹĩ
    0.25
    OperationException
    0.25
    icable
    0.25
     {}.
    0.24
    ichick
    0.24
    trieve
    0.24
    ker
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.