© 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. 108341
    Prev
    Next
    INDEX
    Explanations

    Spreading or moving outwards

    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
    æĶ¹åĬ¨
    -0.28
     -=
    -0.28
    æĴ·
    -0.27
    ä»Ģä¹Īåij¢
    -0.26
    _accessor
    -0.25
     ^=
    -0.25
    ]=[
    -0.25
     &=
    -0.25
     Kling
    -0.25
    ä¸ĵ注äºİ
    -0.24
    POSITIVE LOGITS
    éĻ¡
    0.28
    积æŀģåĵįåºĶ
    0.28
     aff
    0.27
    vice
    0.26
    人群
    0.26
     uncomment
    0.26
     region
    0.25
    çĨ¨
    0.25
    åĨį说
    0.25
     sever
    0.25
    Activations Density 5.825%

    No Known Activations