© 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. 24-TRANSCODER-HP
    7. 150881
    Prev
    Next
    INDEX
    Explanations

    uck/Uk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłæĥħ
    -0.28
    udy
    -0.25
     arter
    -0.25
    åħļç»Ħ
    -0.24
     touch
    -0.24
     centers
    -0.24
    Supplier
    -0.24
     centres
    -0.24
    åĨį说
    -0.23
    亿åħĥ以ä¸Ĭ
    -0.23
    POSITIVE LOGITS
    Purpose
    0.28
    -under
    0.26
     Cres
    0.26
    èĥ¶
    0.25
    缩
    0.25
    ãĤĦãĤī
    0.25
    åľľ
    0.25
    ä¸ĭ
    0.24
    kart
    0.24
    æľīæľºä¼ļ
    0.24
    Activations Density 1.148%

    No Known Activations