© 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. 7750
    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
     blanks
    -0.28
    责任åĪ¶
    -0.28
     okre
    -0.27
     suction
    -0.26
     blank
    -0.26
     az
    -0.26
    pass
    -0.25
    ux
    -0.25
    ou
    -0.25
    passes
    -0.25
    POSITIVE LOGITS
    人å±ħ
    0.33
    mojom
    0.28
     keyed
    0.25
    é«ij
    0.25
    ("{\"
    0.25
    жÑĥ
    0.25
    รว
    0.24
    NY
    0.24
     faithfully
    0.24
    æĢİä¹Īçľĭ
    0.24
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.