© 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. 130679
    Prev
    Next
    INDEX
    Explanations

    Diverse, seemingly random texts

    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
    çij¾
    -0.26
     periodically
    -0.26
     depressed
    -0.24
    çİĩåħĪ
    -0.24
    误导
    -0.24
    DownList
    -0.23
    èµ·ä¼ı
    -0.23
    beit
    -0.23
    ollower
    -0.23
    åį³ä¾¿
    -0.23
    POSITIVE LOGITS
    èªĵ
    0.27
    æĮŀ
    0.25
     NTN
    0.25
    åĽĬ
    0.25
    ¶Ī
    0.25
    æīĵéĢļ
    0.25
    جر
    0.24
    åŃĹ第
    0.24
     shack
    0.23
     locality
    0.23
    Activations Density 0.004%

    No Known Activations