© 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. 112601
    Prev
    Next
    INDEX
    Explanations

    Fields of study ending "al"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    人çĶŁçļĦ
    -0.24
    让åѦçĶŁ
    -0.24
    人éĻħ
    -0.24
    å¼ŁåŃIJ
    -0.23
    tyard
    -0.23
    mented
    -0.23
    碰åĪ°
    -0.23
    \Exceptions
    -0.23
    ç¾İ好çļĦ
    -0.22
    åŀŁ
    -0.22
    POSITIVE LOGITS
     rig
    0.28
    å®ļ
    0.25
    fw
    0.25
     shaken
    0.24
    ä¸Ģè´¯
    0.24
     pans
    0.24
    -appointed
    0.24
    ORTH
    0.24
    vent
    0.24
    IVEN
    0.23
    Activations Density 0.024%

    No Known Activations