© 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. 7213
    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
    elin
    -0.30
    åı¸
    -0.29
    anel
    -0.28
    keyCode
    -0.27
     grop
    -0.27
     por
    -0.26
    羣çļĦæĺ¯
    -0.25
    eo
    -0.25
    icio
    -0.25
    apo
    -0.25
    POSITIVE LOGITS
    çĺĹ
    0.27
    èĩªçĦ¶ä¿ĿæĬ¤
    0.25
    建åįİ
    0.25
    çIJ°
    0.25
    cest
    0.25
    leta
    0.25
     descended
    0.24
    usk
    0.24
    åĽ½å¤ĸ
    0.24
     beware
    0.24
    Activations Density 1.164%

    No Known Activations

    This feature has no known activations.