© 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. 63340
    Prev
    Next
    INDEX
    Explanations

    of

    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
    orias
    -0.29
    quals
    -0.28
    /swagger
    -0.26
    entic
    -0.25
     Agencies
    -0.24
    istica
    -0.24
    ILLE
    -0.24
    è¿Ļæł·çļĦè¯Ŀ
    -0.24
    -č↵
    -0.24
     enc
    -0.24
    POSITIVE LOGITS
    è¡ħ
    0.29
     youth
    0.28
    åŀĴ
    0.28
    为人
    0.27
     Maul
    0.27
    çĪ±ä½ł
    0.27
    виÑĤ
    0.27
     blocker
    0.26
    unday
    0.26
     warned
    0.26
    Activations Density 13.559%

    No Known Activations