© 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. 112100
    Prev
    Next
    INDEX
    Explanations

    even

    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
    ivers
    -0.25
    ä½ľçĶ¨
    -0.24
    кÑĢа
    -0.24
     drains
    -0.24
    .ali
    -0.23
    ycastle
    -0.23
    erno
    -0.23
    ivate
    -0.23
    inem
    -0.22
    ä¼Ĭæĭī
    -0.22
    POSITIVE LOGITS
    å°ijæķ°
    0.33
     rarely
    0.33
    å¾®éĩı
    0.32
    å¤įæĿĤçļĦ
    0.32
     ÑģамÑĭÑħ
    0.32
     occasional
    0.30
    åģ¶å°Ķ
    0.29
    å¤įæĿĤ
    0.28
     faint
    0.28
     subtle
    0.28
    Activations Density 0.012%

    No Known Activations