© 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. 196
    Prev
    Next
    INDEX
    Explanations

    of

    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
    åĪĨæµģ
    -0.29
    æł¹æºIJ
    -0.28
    !--
    -0.27
    emark
    -0.27
    ç«ĭåĪ»
    -0.27
     LIABLE
    -0.27
    .group
    -0.26
    å¿«æį·
    -0.25
    ç«ĭåį³
    -0.25
     GROUP
    -0.24
    POSITIVE LOGITS
    纵横
    0.25
    accumulate
    0.25
     tallest
    0.24
    èĦIJ
    0.23
    profession
    0.23
    .toObject
    0.23
    ä¼łè¨Ģ
    0.23
    éĥ½è¯´
    0.23
     widest
    0.23
     pain
    0.23
    Activations Density 0.004%

    No Known Activations