© 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. 141764
    Prev
    Next
    INDEX
    Explanations

    Any

    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
     YT
    -0.30
    å°±æĺ¯åľ¨
    -0.29
    æĺ¯åľ¨
    -0.28
     batching
    -0.28
    å®ŀåľ¨æĺ¯
    -0.27
    ouro
    -0.26
    YST
    -0.25
    ponsor
    -0.25
    ponsors
    -0.24
    çīĤ
    -0.24
    POSITIVE LOGITS
    åĿĩåı¯
    0.34
    éĥ½åı¯ä»¥
    0.34
    CanBe
    0.28
    çŀ¬éĹ´
    0.28
    符åIJĪæĿ¡ä»¶
    0.27
    åį³åı¯
    0.27
    éĥ½ä¼ļæľī
    0.26
     imaginable
    0.26
    -any
    0.26
    ä¸Ģ线
    0.25
    Activations Density 53.020%

    No Known Activations