© 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. 42498
    Prev
    Next
    INDEX
    Explanations

    Metric units prefixes

    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
    ursday
    -0.29
     Stard
    -0.28
     chá»īnh
    -0.28
    社ä¼ļåĮĸ
    -0.28
    äºĭä¸ļåıijå±ķ
    -0.28
    绸
    -0.26
    osi
    -0.25
    åģĩæĹ¥
    -0.25
    åħ¬è¯ģ
    -0.25
    ä¸ĩ个
    -0.24
    POSITIVE LOGITS
    ider
    0.32
    æĪĬ
    0.29
    ipt
    0.27
    ape
    0.26
    ip
    0.26
    ile
    0.26
    ibur
    0.26
    iro
    0.25
    èį¯
    0.25
    iloc
    0.25
    Activations Density 0.001%

    No Known Activations