© 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. 98875
    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
    åIJĦçľģ
    -0.28
    -categories
    -0.25
     stiff
    -0.25
     squ
    -0.25
    /non
    -0.25
     louis
    -0.24
     issuance
    -0.24
     sideways
    -0.24
     spur
    -0.24
     exclus
    -0.24
    POSITIVE LOGITS
    çĶŁæ´»æĸ¹å¼ı
    0.28
    caret
    0.27
    iteDatabase
    0.26
    otonin
    0.26
    gon
    0.26
    itten
    0.25
    jas
    0.25
    æĹłçº¿çĶµ
    0.24
    çļĦè¡Į为
    0.24
    èģĶ
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.