© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64025
    Prev
    Next
    INDEX
    Explanations

    sweet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /open
    -0.28
    éķ¿ä¹ħ
    -0.27
    å¼ĢæĶ¾
    -0.25
    âİŀ
    -0.25
    å¾Īéļ¾
    -0.25
     cen
    -0.24
    âİĽ
    -0.24
     próximo
    -0.24
    OperationException
    -0.24
    åĩłæŃ¥
    -0.24
    POSITIVE LOGITS
    ä¸įåħį
    0.28
     buzz
    0.26
    æĬĢæľ¯åĴĮ
    0.25
    åıįè¿ĩæĿ¥
    0.25
    onica
    0.25
    èµĦ
    0.24
    statt
    0.24
     alternatively
    0.24
    eon
    0.24
    ówki
    0.24
    Activations Density 4.837%

    No Known Activations