© 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. 19-TRANSCODER-HP
    7. 5002
    Prev
    Next
    INDEX
    Explanations

    spam

    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
    èIJľ
    -0.27
    åīįæıIJ
    -0.25
    éĢ»è¾ij
    -0.25
    æīĭ表
    -0.25
    ä¸įä¼ļ
    -0.25
    åĩºåıij
    -0.24
    -parts
    -0.24
    -sem
    -0.23
    é¢ĺ
    -0.23
    ellation
    -0.23
    POSITIVE LOGITS
     thôi
    0.28
    å§Ķ
    0.27
     Activ
    0.27
     mish
    0.27
    drops
    0.26
    adh
    0.26
    activation
    0.25
    ç½ijæ°ij
    0.25
    oz
    0.25
    ivity
    0.24
    Activations Density 0.090%

    No Known Activations