© 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. 63232
    Prev
    Next
    INDEX
    Explanations

    beginning and end points

    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
    opo
    -0.27
    å»ĵ
    -0.26
    tober
    -0.26
    -Disposition
    -0.25
    ores
    -0.25
     sug
    -0.24
    ipel
    -0.24
    ;base
    -0.24
     nir
    -0.23
    è¿«
    -0.23
    POSITIVE LOGITS
    zier
    0.27
    consult
    0.25
    ä¸¥æł¼æī§è¡Į
    0.24
    idth
    0.24
     Fen
    0.23
    fon
    0.23
    ength
    0.23
    碼
    0.23
    ä½ıæĪ¿
    0.23
    è§ŀ
    0.23
    Activations Density 1.990%

    No Known Activations