© 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. 32-TRANSCODER-HP
    7. 41972
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/locations/names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initely
    -0.28
    åĨįéĢł
    -0.27
    æĹ¥æĬ¥éģĵ
    -0.26
    éĺ»åĬĽ
    -0.26
    çĶŁäº§èĥ½åĬĽ
    -0.24
    ẳ
    -0.24
    红线
    -0.24
    åĮ»çĸĹåį«çĶŁ
    -0.24
    edar
    -0.24
    æĭĻ
    -0.24
    POSITIVE LOGITS
    æ½®
    0.29
    LES
    0.28
    lev
    0.27
     Cham
    0.27
    gap
    0.26
    IPP
    0.25
    èĮ¹
    0.25
    åĶĨ
    0.24
    ä¼łç»Ł
    0.24
    åıī
    0.24
    Activations Density 0.000%

    No Known Activations