© 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. 98280
    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
    æIJŃ
    -0.27
     sin
    -0.27
     fast
    -0.26
    æݨ
    -0.26
     med
    -0.26
    osomes
    -0.25
     kit
    -0.25
    çĸı
    -0.24
    kov
    -0.24
     squ
    -0.24
    POSITIVE LOGITS
    nof
    0.27
    _guide
    0.26
    umeric
    0.25
    辦çIJĨ
    0.25
    DEST
    0.25
    emics
    0.24
     defining
    0.24
    itary
    0.23
     buttonText
    0.23
    çļĦéĩį大
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.