© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4728
    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
     Oh
    -0.27
    ain
    -0.26
    ONS
    -0.26
     лÑİ
    -0.25
     friction
    -0.25
     AH
    -0.25
    oh
    -0.25
    ah
    -0.24
    _FE
    -0.24
    AH
    -0.24
    POSITIVE LOGITS
    说çļĦæĺ¯
    0.27
     mũi
    0.25
    pcodes
    0.25
    æĬķèµĦé¢Ŀ
    0.24
    说æĺ¯
    0.24
    éĥ¨åĪĨåĨħ容
    0.24
     radi
    0.24
    +",
    0.24
    çĵ£
    0.24
    çij·
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.