© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 19
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    没è§ģè¿ĩ
    -0.27
    çĶŁäº§çļĦ
    -0.26
     rue
    -0.26
    åģ¥èº«æĪ¿
    -0.25
    没æľīæĥ³åĪ°
    -0.25
    çĶŁæ´»çļĦ
    -0.25
    ensem
    -0.24
    龸çİĭ
    -0.24
    éĹ·
    -0.23
    ILLA
    -0.23
    POSITIVE LOGITS
    icer
    0.26
    _dt
    0.26
    лад
    0.25
     Ore
    0.25
    etre
    0.24
    对ä¸ŃåĽ½
    0.24
    è¿ŀ线
    0.24
    åĽŀåįĩ
    0.24
     Islands
    0.23
    =sys
    0.23
    Activations Density 5.735%

    No Known Activations