© 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. 8562
    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
    onda
    -0.29
     Mã
    -0.26
    ä¸Ģçĵ¶
    -0.26
     eben
    -0.24
    leaf
    -0.24
    shots
    -0.24
    	record
    -0.23
    obra
    -0.23
    _typ
    -0.23
    PLIED
    -0.23
    POSITIVE LOGITS
    åĪĿæľŁ
    0.28
    ä¸ŃæľŁ
    0.26
    模æĭŁ
    0.26
     multiple
    0.25
    p
    0.24
    çĶ¨æĪ·æıIJä¾Ľ
    0.24
    Multiple
    0.24
    常æĢģ
    0.23
    ×
    0.23
     simulation
    0.23
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.