© 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. 140997
    Prev
    Next
    INDEX
    Explanations

    Uncertainty and hedging

    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
    xE
    -0.27
    èĢģåŃIJ
    -0.27
     Har
    -0.27
    /single
    -0.26
    å°±æĺ¯è¦ģ
    -0.26
     du
    -0.24
    inth
    -0.24
    åľ¨ä¸Ģ个
    -0.24
    -years
    -0.23
    åľ¨åĽ½å¤ĸ
    -0.23
    POSITIVE LOGITS
    nop
    0.28
    ä¸Ľä¹¦
    0.26
    rett
    0.26
    éĿ¢
    0.25
    -collapse
    0.25
    gaard
    0.25
     zag
    0.25
    _behavior
    0.25
    ög
    0.24
    åıĬåħ¶ä»ĸ
    0.24
    Activations Density 5.184%

    No Known Activations