© 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. 6010
    Prev
    Next
    INDEX
    Explanations

    image/video

    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
    æī§
    -0.29
    spa
    -0.27
    å§Ķ
    -0.26
    ixo
    -0.26
    æĽ´åħ·
    -0.25
    å§Ķä¼ļ
    -0.24
    æŁIJäºĽ
    -0.24
     notch
    -0.24
     Hoy
    -0.24
    åľ¨æ¸¸æĪıä¸Ń
    -0.24
    POSITIVE LOGITS
    æļ§
    0.33
     accommod
    0.29
    æīĭä¸Ĭ
    0.28
     tÃł
    0.28
    cle
    0.26
    -figure
    0.25
     Infos
    0.25
     disse
    0.25
    zel
    0.24
    zet
    0.24
    Activations Density 0.057%

    No Known Activations