© 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. 88106
    Prev
    Next
    INDEX
    Explanations

    Code-related keywords

    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
    æľīçļĦ
    -0.27
    åı¦è¡Į
    -0.26
    essler
    -0.26
    resher
    -0.26
     practices
    -0.25
    ated
    -0.24
    ãģ»ãģ¼
    -0.24
    ä¸Ģ侧
    -0.24
     regarding
    -0.24
     deeds
    -0.24
    POSITIVE LOGITS
    åĪĺæµ·
    0.27
     FT
    0.26
     irony
    0.25
    è°ģçŁ¥éģĵ
    0.25
    åĽ½éĻħåIJĪä½ľ
    0.25
    _FT
    0.25
    onation
    0.24
     USERNAME
    0.24
    åıĮåIJij
    0.24
    æĪIJ为ä¸ŃåĽ½
    0.24
    Activations Density 0.001%

    No Known Activations