© 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. 98049
    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
     Owens
    -0.24
    çıŃç»Ħ
    -0.24
    ewise
    -0.23
     Craft
    -0.23
     Klaus
    -0.23
    дан
    -0.23
    oder
    -0.23
     Brooks
    -0.23
    ['__
    -0.23
    ially
    -0.22
    POSITIVE LOGITS
    ä¸Ģæľ¬
    0.29
    PyObject
    0.26
    åħĥå®Ŀ
    0.25
    irut
    0.25
    åħįéĻ¤
    0.25
    ä¸ĢåIJį
    0.24
    orias
    0.24
    è¿ĩéĶĻ
    0.23
    éĻĦè¿ijçļĦ
    0.23
    ----------↵
    0.23
    Activations Density 0.039%

    No Known Activations

    This feature has no known activations.