© 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. 98445
    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
    arto
    -0.27
    èīºæľ¯åĵģ
    -0.26
     arts
    -0.26
    åĿĬ
    -0.25
    éĢıæ°Ķ
    -0.24
    âį£
    -0.24
     enclave
    -0.23
     gadgets
    -0.23
    å£ij
    -0.23
    uant
    -0.23
    POSITIVE LOGITS
    çĨŁ
    0.26
    ç±³
    0.24
    selectAll
    0.24
    istribution
    0.24
     Kingdom
    0.24
    rece
    0.24
    /repos
    0.23
    warm
    0.23
    ÑĢан
    0.23
     Queen
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.