© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 167
    Prev
    Next
    INDEX
    Explanations

    Redistribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĤек
    -0.29
    olum
    -0.25
    ourcem
    -0.24
     lä
    -0.24
     relief
    -0.23
     componentWill
    -0.23
     spill
    -0.23
    åľ¨éĩĮéĿ¢
    -0.23
     softened
    -0.23
    è°IJ
    -0.23
    POSITIVE LOGITS
     anthrop
    0.29
    izen
    0.28
    phia
    0.26
    ifique
    0.26
    issy
    0.26
    éļį
    0.25
    antro
    0.25
    èĩªåĬ©
    0.24
    YSIS
    0.24
    主ä¹īæĢĿæĥ³
    0.24
    Activations Density 0.142%

    No Known Activations