© 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. 9025
    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
     intox
    -0.28
    ät
    -0.26
    缸å½ĵ
    -0.26
    awi
    -0.25
    串
    -0.25
    侩
    -0.24
    ä¸Ģç»Ħ
    -0.24
    nar
    -0.23
    ä»Ĭ
    -0.23
     enfer
    -0.23
    POSITIVE LOGITS
    èIJ½
    0.30
    èIJ½åĪ°
    0.25
    éĺħ读åħ¨æĸĩ
    0.25
    _markers
    0.25
     acceptance
    0.25
    éĹ³
    0.25
    воз
    0.25
     exped
    0.24
    åħ¨ç¨ĭ
    0.24
    igram
    0.23
    Activations Density 1.625%

    No Known Activations

    This feature has no known activations.