© 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. 98097
    Prev
    Next
    INDEX
    Explanations

    code

    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
    åı¯è§Ĩ
    -0.32
    ogh
    -0.29
     Renders
    -0.27
    åįļ
    -0.26
    iard
    -0.26
    èĻ½çĦ¶æĺ¯
    -0.25
    atori
    -0.25
    dart
    -0.25
    åĪ¶åº¦æĶ¹éĿ©
    -0.25
    ä¸ĢçĤ¹åĦ¿
    -0.25
    POSITIVE LOGITS
     pres
    0.27
    mask
    0.27
     '",
    0.25
     classNames
    0.24
    0.24
     Anonymous
    0.24
    èĻ±
    0.23
    esis
    0.23
    éļIJ身
    0.23
    带ä¸Ĭ
    0.23
    Activations Density 0.003%

    No Known Activations