© 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. 7763
    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
    pects
    -0.31
    iesz
    -0.28
    亲身
    -0.27
    æµ®
    -0.27
     rel
    -0.26
    渤海
    -0.26
    ç´«
    -0.26
     oversh
    -0.25
    elho
    -0.25
    饱
    -0.25
    POSITIVE LOGITS
    çĩĶ
    0.25
    å·§åħĭ
    0.25
    /System
    0.25
    åĬ±
    0.24
    rees
    0.24
    /helper
    0.24
    TY
    0.23
     Cooperative
    0.23
    æŀIJ
    0.23
    ategy
    0.23
    Activations Density 0.058%

    No Known Activations

    This feature has no known activations.