© 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. 111784
    Prev
    Next
    INDEX
    Explanations

    international, foreign travel

    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
    社ä¼ļæķĪçĽĬ
    -0.29
     bes
    -0.29
    ves
    -0.28
    лов
    -0.28
     nationwide
    -0.27
    åħ¨ç¤¾ä¼ļ
    -0.26
    ekyll
    -0.25
    è°ģ
    -0.24
    åħ¨åĽ½
    -0.24
    åľ¨åħ¨åĽ½
    -0.24
    POSITIVE LOGITS
     Bars
    0.28
     pul
    0.28
    antine
    0.26
     rejection
    0.26
     FETCH
    0.25
    unded
    0.25
    èĦī
    0.25
    Cab
    0.25
     capitals
    0.25
    èĦĪ
    0.24
    Activations Density 0.069%

    No Known Activations