© 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. 97454
    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
     men
    -0.26
    imar
    -0.25
    ıs
    -0.25
    .exports
    -0.24
     Men
    -0.24
    quiring
    -0.23
     Hen
    -0.23
    Backing
    -0.22
    voir
    -0.22
    èle
    -0.22
    POSITIVE LOGITS
    æİ¥
    0.28
    ä¿¡å¿ĥ
    0.28
    é£İåIJ¹
    0.26
    驶
    0.24
    Bell
    0.23
    就读
    0.23
    hos
    0.23
    ockets
    0.22
    cv
    0.22
    '}}
    0.22
    Activations Density 0.072%

    No Known Activations

    This feature has no known activations.