© 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. 32-TRANSCODER-HP
    7. 41298
    Prev
    Next
    INDEX
    Explanations

    mixed topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    空ä¸Ń
    -0.28
    JE
    -0.26
     sur
    -0.24
    cripcion
    -0.24
     splitter
    -0.24
     crew
    -0.23
    éħĴ
    -0.23
    _PY
    -0.23
    æĮ¤
    -0.23
    çľĭ好
    -0.23
    POSITIVE LOGITS
    еÑĤÑĮ
    0.30
    еб
    0.28
    åŃIJ
    0.28
    æĸ°éĻĪ代谢
    0.27
    ices
    0.27
    éĻĦ件
    0.27
    åĪ©
    0.27
    åīª
    0.26
    Thor
    0.25
    Sab
    0.24
    Activations Density 0.002%

    No Known Activations