© 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. 130444
    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
     manh
    -0.29
    ENUM
    -0.27
     доволÑĮ
    -0.26
    æĮij
    -0.26
     martyr
    -0.25
    çĮĸ
    -0.25
    hread
    -0.25
    éķ¿å®ī
    -0.24
    綾
    -0.24
    秦çļĩ
    -0.24
    POSITIVE LOGITS
    etti
    0.26
    üt
    0.25
    IVA
    0.25
    itude
    0.25
    çļĦå®ŀåĬĽ
    0.24
    elper
    0.24
    esen
    0.24
    iva
    0.24
    ety
    0.23
    èµĽ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.