© 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. 4884
    Prev
    Next
    INDEX
    Explanations

    ://

    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
    ä¸İåħ¶
    -0.30
     getHeight
    -0.28
    æľĢé«ĺçļĦ
    -0.27
     trait
    -0.26
    åĶ¯ä¸ĢçļĦ
    -0.25
    ä»»æĦı
    -0.25
    uhl
    -0.25
    ä»»
    -0.24
    æŃ£
    -0.24
    rones
    -0.24
    POSITIVE LOGITS
    xFFF
    0.29
     Parliamentary
    0.25
     discharged
    0.25
    andan
    0.24
    itics
    0.24
    ä¸Ģæ³¢
    0.24
     AST
    0.23
    --+
    0.23
    _parsed
    0.23
     Victorian
    0.23
    Activations Density 0.025%

    No Known Activations