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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5921
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩªå·±çļĦ
    -0.35
     personal
    -0.35
    å±ŀäºİèĩªå·±
    -0.32
     own
    -0.31
     personally
    -0.30
    èĩªå·±
    -0.30
    udu
    -0.29
     ÑģебÑı
    -0.28
    stadt
    -0.28
    ä½łèĩªå·±
    -0.28
    POSITIVE LOGITS
    两åIJį
    0.37
    两åıª
    0.36
    两个
    0.35
    çĶ·å¥³
    0.35
    两个人
    0.35
     beiden
    0.33
    两款
    0.33
     dwóch
    0.32
    åħ©åĢĭ
    0.32
    å¤ļ个
    0.31
    Activations Density 0.016%

    No Known Activations