© 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. 141038
    Prev
    Next
    INDEX
    Explanations

    leadership

    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
    çŃ·åŃIJ
    -0.28
    çĤ¹
    -0.25
     Thick
    -0.25
    ä¼łåĬ¨
    -0.25
    itty
    -0.25
    ijn
    -0.25
    çĶµæľº
    -0.25
    çļĦå°±æĺ¯
    -0.25
    å°±æĥ³
    -0.24
     Indicates
    -0.24
    POSITIVE LOGITS
    æĸĹ
    0.27
     society
    0.26
     history
    0.26
     neglected
    0.25
     standardized
    0.25
     neglect
    0.25
    apy
    0.25
     mixture
    0.25
    èıŁ
    0.25
    鬥
    0.24
    Activations Density 6.466%

    No Known Activations