© 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. 130949
    Prev
    Next
    INDEX
    Explanations

    anniversaries

    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
    imiento
    -0.30
    åŁİå¸ĤçļĦ
    -0.27
    olas
    -0.26
    ROME
    -0.26
     Americans
    -0.25
    -site
    -0.25
    éĩįè¦ģåĨħ容
    -0.25
    RootElement
    -0.24
    åŃ¦æł¡çļĦ
    -0.24
    ált
    -0.23
    POSITIVE LOGITS
     history
    0.28
    åIJİåı°
    0.27
     fulfil
    0.26
    æĦıè§ģåıįé¦Ī
    0.24
     settles
    0.24
     Feedback
    0.23
    ä¸Ĭä¸ĸ纪
    0.23
    æł¼
    0.23
    èµ°åĬ¿åĽ¾
    0.23
    èĶ¡
    0.22
    Activations Density 0.009%

    No Known Activations