© 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. 141165
    Prev
    Next
    INDEX
    Explanations

    Citation Markers

    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
    çļĦçŁ¥è¯Ĩ
    -0.27
    anus
    -0.26
    аÑĢÑĮ
    -0.25
    rien
    -0.24
    å¾Īæľī
    -0.24
    -care
    -0.24
     care
    -0.24
     formatter
    -0.24
     hint
    -0.24
     gratuitement
    -0.23
    POSITIVE LOGITS
    åī¥
    0.27
    zw
    0.26
    angu
    0.26
    èľ»
    0.26
    isse
    0.26
    èĢĹ
    0.25
    gap
    0.25
    æ¯ıéļĶ
    0.24
     rap
    0.24
    )="
    0.24
    Activations Density 2.655%

    No Known Activations