© 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. 30-TRANSCODER-HP
    7. 96508
    Prev
    Next
    INDEX
    Explanations

    eye/ocular related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿŁ
    -0.35
    pole
    -0.32
    身
    -0.28
     cảnh
    -0.28
     dressed
    -0.28
    éĽ¾
    -0.28
     Templ
    -0.27
    /display
    -0.26
    zburg
    -0.26
    izards
    -0.25
    POSITIVE LOGITS
    iterations
    0.27
    ocard
    0.27
    çĶŁäº§åĴĮ
    0.26
    çĹĪ
    0.25
    亡
    0.25
    å¤ı天
    0.25
     BTN
    0.24
    çī©ä»·
    0.24
    èį¯ä¸ļ
    0.24
    adio
    0.23
    Activations Density 0.109%

    No Known Activations