© 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. 112198
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å½±
    -0.26
    第ä¸ī次
    -0.26
     COPYING
    -0.24
    æłĵ
    -0.24
    çģµ
    -0.24
    ientos
    -0.23
    acles
    -0.23
    .Singleton
    -0.23
    æł·
    -0.23
     ring
    -0.23
    POSITIVE LOGITS
    icer
    0.26
     impover
    0.26
    blo
    0.24
    getRoot
    0.24
     "*.
    0.23
     surviving
    0.23
     rá»Ŀi
    0.23
    ÙģصÙĦ
    0.23
     froze
    0.22
    å®ĥæĺ¯
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.