© 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. 131183
    Prev
    Next
    INDEX
    Explanations

    readily

    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
    omite
    -0.28
     Tucker
    -0.27
    htt
    -0.27
    çĶ¨å¿ĥ
    -0.25
    Lite
    -0.25
    åĪ»æĦı
    -0.25
    pring
    -0.24
    CUS
    -0.24
    ä»Ģä¹Īæĺ¯
    -0.24
    æī«
    -0.23
    POSITIVE LOGITS
    ider
    0.28
    loom
    0.26
    oward
    0.25
    ursed
    0.25
    (isinstance
    0.24
    ugal
    0.23
    iram
    0.23
    ivos
    0.23
    epend
    0.22
    à¹īาย
    0.22
    Activations Density 0.104%

    No Known Activations