© 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. 87972
    Prev
    Next
    INDEX
    Explanations

    Punctuation/code symbols

    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
    ´Ģ
    -0.28
     génér
    -0.26
    åĽĽä½į
    -0.25
    ä¸įåĥı
    -0.25
    ä¸Ńå¿ĥ主任
    -0.25
    icro
    -0.24
    åĬŁ
    -0.24
    足
    -0.24
    ä»»ä½ķä¸Ģ个
    -0.24
    bern
    -0.23
    POSITIVE LOGITS
    otope
    0.28
     other
    0.25
     newer
    0.25
     Reef
    0.25
    omi
    0.25
    itch
    0.25
     worse
    0.25
     nearer
    0.25
    ynamo
    0.24
     simpler
    0.24
    Activations Density 0.002%

    No Known Activations