© 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. 111899
    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
     dif
    -0.24
    ndo
    -0.24
    解æĶ¾
    -0.24
    äºĨä¸Ģåı£
    -0.24
     bri
    -0.24
    ãĤĬãģ¾ãģĹãģŁ
    -0.24
    æĪ·ç±į
    -0.23
    icer
    -0.23
    å·²ç»ıæĺ¯
    -0.23
     snapshots
    -0.23
    POSITIVE LOGITS
     explicit
    0.28
     stren
    0.26
    Äħc
    0.25
    cord
    0.25
    æŶèĬĤ
    0.25
    porto
    0.25
     ideal
    0.25
    ymbol
    0.24
    符åı·
    0.24
    uren
    0.24
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.