© 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. 108162
    Prev
    Next
    INDEX
    Explanations

    Growth, life

    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
     Ones
    -0.31
    åĩ¡
    -0.29
    åIJijå¾Ģ
    -0.28
     versa
    -0.25
    代表
    -0.25
    æĩĤ
    -0.25
    iem
    -0.25
    大éĺŁ
    -0.25
    __).
    -0.24
    %=
    -0.24
    POSITIVE LOGITS
     slot
    0.26
    éŁª
    0.26
     IMPLEMENT
    0.25
    åĻ¨
    0.25
    slots
    0.25
    æ¯ĽåŃĶ
    0.24
    ropri
    0.24
     slots
    0.24
    åĹĸ
    0.24
    slot
    0.24
    Activations Density 6.467%

    No Known Activations