© 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. 142226
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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
    çIJ¦
    -0.28
    ville
    -0.28
     adventures
    -0.28
    æŁ¥æī¾
    -0.28
     lectures
    -0.25
     retract
    -0.25
    æ£Ģç´¢
    -0.25
     Jeffrey
    -0.25
     trails
    -0.25
     lect
    -0.25
    POSITIVE LOGITS
    éŁ³ä¹IJ
    0.27
    hib
    0.27
    ой
    0.26
    emons
    0.25
    uth
    0.25
    åħ¼åħ·
    0.25
    ä¿ĥè¿Ľ
    0.25
    piring
    0.24
    ä½Ĩ
    0.24
    ifiable
    0.24
    Activations Density 0.770%

    No Known Activations