© 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. 6365
    Prev
    Next
    INDEX
    Explanations

    page

    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
    éĽĦåİļ
    -0.24
    æĭ³å¤´
    -0.23
    åı¯éĿłçļĦ
    -0.23
    æį
    -0.23
    éĽ³
    -0.23
    azole
    -0.23
    illet
    -0.23
    (Il
    -0.22
    ä¸İåıijå±ķ
    -0.22
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.22
    POSITIVE LOGITS
    -wise
    0.26
     slate
    0.25
    éĿ¢ç§¯
    0.24
    tá
    0.24
    åijĺ
    0.24
    ointment
    0.24
    åºŃ
    0.24
    تأ
    0.23
    å»Ĭ
    0.23
    ár
    0.23
    Activations Density 1.992%

    No Known Activations