© 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. 4804
    Prev
    Next
    INDEX
    Explanations

    Approximation/Quantity

    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
    åĨįä¸Ģ次
    -0.28
    强èĢħ
    -0.28
    çĶŁæ´»åľ¨
    -0.27
    odule
    -0.26
    åĩŃä»Ģä¹Ī
    -0.25
    [vi
    -0.25
    çļĦåĬªåĬĽ
    -0.25
    estring
    -0.25
    eters
    -0.24
     Too
    -0.24
    POSITIVE LOGITS
     curs
    0.28
    åľĴ
    0.27
    åĽŃ
    0.27
     Unicorn
    0.26
     outnumber
    0.26
     uniquely
    0.26
     ampl
    0.25
     pur
    0.25
     peach
    0.25
    phis
    0.25
    Activations Density 0.457%

    No Known Activations