© 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. 22-TRANSCODER-HP
    7. 98200
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cal
    -0.28
    mis
    -0.28
    两ä½į
    -0.27
    æ´¾
    -0.27
     traced
    -0.27
    è¾Ī
    -0.27
    åĩłä½į
    -0.26
    éľĪ
    -0.26
    cur
    -0.26
    åĩºåľŁ
    -0.25
    POSITIVE LOGITS
     himself
    0.27
    åŁł
    0.25
     former
    0.25
     latter
    0.24
     Former
    0.23
    site
    0.23
     Denis
    0.23
    retch
    0.23
     Observer
    0.23
     specifier
    0.23
    Activations Density 0.004%

    No Known Activations