© 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. 130703
    Prev
    Next
    INDEX
    Explanations

    journal studies

    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
    buzz
    -0.28
    è¿ĻäºĽä¸ľè¥¿
    -0.27
     cleans
    -0.26
    -addons
    -0.25
    æĢİä¹Ī说
    -0.24
    Coordinator
    -0.24
     scal
    -0.24
    ä»ĸ们éĥ½
    -0.23
    è¿Ļä¸ī个
    -0.23
    ouples
    -0.23
    POSITIVE LOGITS
     radi
    0.26
    书éĿ¢
    0.24
    ingleton
    0.24
     Radi
    0.23
     regimes
    0.23
    INS
    0.23
     insufficient
    0.23
    ında
    0.23
    ä¹ĭä½Ļ
    0.22
     Bd
    0.22
    Activations Density 0.028%

    No Known Activations