© 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. 129633
    Prev
    Next
    INDEX
    Explanations

    Lists of categories

    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
    å§ĵ
    -0.29
    类似äºİ
    -0.28
     similarly
    -0.28
    åIJij
    -0.27
     Similarly
    -0.26
     similar
    -0.26
    ãģ£ãģ¨
    -0.26
    Similarly
    -0.26
    类似
    -0.26
    è¦ģä¹Ī
    -0.25
    POSITIVE LOGITS
     equipments
    0.26
    roach
    0.24
    HAS
    0.24
    çļĦåīįæıIJä¸ĭ
    0.24
    äºĨ解ä¸Ģä¸ĭ
    0.24
    oundation
    0.24
    室å¤ĸ
    0.24
    缩水
    0.24
    æĬĬè¿ĻäºĽ
    0.24
    èµ·çłģ
    0.24
    Activations Density 0.029%

    No Known Activations