© 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. 112201
    Prev
    Next
    INDEX
    Explanations

    scientific, medical research

    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
    çīĪæĿĥæīĢæľī
    -0.30
     possible
    -0.29
    aticon
    -0.29
     since
    -0.27
    lingen
    -0.27
    ahi
    -0.26
    possible
    -0.26
    since
    -0.26
    \Context
    -0.25
    ellt
    -0.25
    POSITIVE LOGITS
    ãģ§ãģĹãģŁãģĮ
    0.29
    ãģĹãģ¦ãģĦãģ¾ãģĹãģŁ
    0.29
     seemed
    0.28
    ãģ§ãģĹãģŁ
    0.28
     was
    0.28
    était
    0.28
    åıijæĮ¥äºĨ
    0.27
    è¾¾åĪ°äºĨ
    0.27
     belonged
    0.27
     consistently
    0.27
    Activations Density 0.058%

    No Known Activations