© 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. 98437
    Prev
    Next
    INDEX
    Explanations

    with

    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
     homepage
    -0.28
    ç¥ģ
    -0.26
     Homepage
    -0.26
    交æį¢
    -0.24
    lich
    -0.24
    Na
    -0.24
    åIJŃ
    -0.23
     NUnit
    -0.23
    çĪ¬ä¸Ĭ
    -0.23
    âĹ»
    -0.23
    POSITIVE LOGITS
    rä
    0.28
    imate
    0.26
    unkt
    0.26
     Plain
    0.26
    plain
    0.25
    çļĦæķ°éĩı
    0.25
     Hint
    0.25
    宾
    0.25
    ä¸ĸ人
    0.25
    èģĬ
    0.24
    Activations Density 0.048%

    No Known Activations