© 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. 204
    Prev
    Next
    INDEX
    Explanations

    inic

    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
    åĮ»æ²»
    -0.24
    _Success
    -0.24
    icens
    -0.24
     Airlines
    -0.23
    SWG
    -0.23
    gam
    -0.23
    èĩªåĪ¶
    -0.23
    鹫
    -0.23
     deepest
    -0.23
    ablish
    -0.23
    POSITIVE LOGITS
    è¿Ļæĸ¹éĿ¢
    0.26
     Lone
    0.25
    rase
    0.25
     çĽ
    0.24
     singly
    0.24
    tor
    0.24
    /ajax
    0.23
    Direct
    0.23
     gerade
    0.23
     åĽ
    0.23
    Activations Density 0.295%

    No Known Activations