© 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. 141901
    Prev
    Next
    INDEX
    Explanations

    clearly

    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
    迹
    -0.28
    ublic
    -0.27
    iter
    -0.27
    Bel
    -0.27
    æľ¯
    -0.26
    ä»Ģ
    -0.26
     Cur
    -0.26
     cite
    -0.26
    æĿĢ
    -0.26
    enses
    -0.25
    POSITIVE LOGITS
    ;element
    0.33
     LLP
    0.28
     Elli
    0.27
    :frame
    0.26
    igator
    0.25
    éĵ
    0.25
    uki
    0.25
    spb
    0.24
    ç½ijé¦ĸ页
    0.24
    igraph
    0.23
    Activations Density 32.748%

    No Known Activations