© 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. 107258
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     McCabe
    -0.33
    ä¼¼
    -0.27
    è®°
    -0.26
    ãĤ¹ãĤ¿ãĥ³
    -0.24
    posted
    -0.24
    strap
    -0.24
    OSH
    -0.24
    é¾Ľ
    -0.24
    Favorites
    -0.23
    ollo
    -0.23
    POSITIVE LOGITS
     equ
    0.26
    æ¯ĶåĪ©
    0.25
    onest
    0.25
     plunge
    0.25
    ä¼ģä¸ļåĴĮ
    0.25
     rue
    0.24
     Audrey
    0.23
     Herm
    0.23
     Rue
    0.23
    itarian
    0.23
    Activations Density 30.763%

    No Known Activations