© 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. 88263
    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
    åĮĻ
    -0.25
    讼
    -0.25
    dest
    -0.25
     fed
    -0.25
    åĪĨæĶ¯
    -0.24
    ,ev
    -0.24
     ved
    -0.24
    +Sans
    -0.24
     EV
    -0.24
    dda
    -0.24
    POSITIVE LOGITS
    aseline
    0.29
    ï¼ģãĢį
    0.28
    å¹´åīį
    0.26
    管çIJĨæ°´å¹³
    0.26
     ún
    0.25
    __č↵
    0.25
     __________________↵↵
    0.25
     ____
    0.25
    __;↵
    0.24
    ihan
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.