© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97297
    Prev
    Next
    INDEX
    Explanations

    Improve life or make easier

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    çī¹æ®ĬçļĦ
    -0.29
    special
    -0.26
    elsen
    -0.25
     listened
    -0.25
    ç³»
    -0.25
    Alter
    -0.25
    AMI
    -0.24
    å¾Ĺ天
    -0.24
    ä¸İæѤ
    -0.24
    aks
    -0.23
    POSITIVE LOGITS
    é¤IJ
    0.25
    æű
    0.25
    ढ
    0.25
     perg
    0.24
    æĥ³è±¡
    0.24
     compartment
    0.23
    timeofday
    0.23
    æľ¬èĥ½
    0.23
    åĸĿèĮ¶
    0.23
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.23
    Activations Density 0.005%

    No Known Activations