© 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. 87321
    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
    è¾ķ
    -0.28
    ç¾İåĽ½äºº
    -0.27
    ä¸Ģ件äºĭ
    -0.25
    åħµé©¬
    -0.25
    ilon
    -0.25
     MySqlCommand
    -0.24
    âĶĮ
    -0.24
     overrun
    -0.24
     crian
    -0.24
    éĤ£ä½ł
    -0.24
    POSITIVE LOGITS
    è¯ģå®ŀ
    0.29
    backs
    0.28
    æĺĵ
    0.25
    æĪIJè´¥
    0.25
    é¢ĺ缮
    0.24
    çŃī级
    0.24
    ipse
    0.24
    elia
    0.24
     quickest
    0.24
    pty
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.