© 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. 99111
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    ely
    -0.26
    å·¥ä½ľä¸Ń
    -0.25
    adamente
    -0.25
    رÙĪÙĨ
    -0.25
    &
    -0.25
     Thá»Ŀi
    -0.24
    etro
    -0.24
    ilon
    -0.24
    åıijè¨Ģ人
    -0.24
    thora
    -0.24
    POSITIVE LOGITS
    /Register
    0.29
    æĬĢæľ¯åĴĮ
    0.28
    æ±ŁåĮĹ
    0.26
    çIJĨ解åĴĮ
    0.26
    -kind
    0.25
     пеÑģ
    0.25
    éĵį
    0.25
     shorts
    0.25
    олж
    0.24
    è´¨éĩıåĴĮ
    0.24
    Activations Density 0.010%

    No Known Activations