© 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. 88223
    Prev
    Next
    INDEX
    Explanations

    Rights

    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
    çĨŁæĤīçļĦ
    -0.27
     бÑĥд
    -0.26
     бÑĥдÑĥ
    -0.25
    浸
    -0.25
    æĿ²
    -0.25
    ç²ī
    -0.24
    dog
    -0.24
     ÃĤu
    -0.24
    æĪ¿
    -0.24
    .zip
    -0.24
    POSITIVE LOGITS
    .instant
    0.26
     roy
    0.26
     react
    0.24
    èIJ¥éĢł
    0.24
    .WindowManager
    0.24
     Erdogan
    0.23
     dresser
    0.23
    åĩĢåĪ©æ¶¦
    0.23
    enticated
    0.23
    awi
    0.23
    Activations Density 0.101%

    No Known Activations