© 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. 88162
    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
    éĢł
    -0.32
    éĹª
    -0.28
    åįģåŃĹ
    -0.25
    å·¥ä½ľå²Ĺä½į
    -0.25
    ä¸Ģåı¥è¯Ŀ
    -0.25
     '**
    -0.25
    .FONT
    -0.25
     §§
    -0.24
    ista
    -0.24
     boss
    -0.24
    POSITIVE LOGITS
    RV
    0.29
    涤
    0.26
    ehler
    0.26
    Rails
    0.26
     çift
    0.25
     vidéo
    0.25
    MediaType
    0.25
     ÐłÐµÑģпÑĥблик
    0.25
     nop
    0.24
     rak
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.