© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142517
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    Negative Logits
    enk
    -0.27
    CardContent
    -0.26
    ise
    -0.25
    events
    -0.25
    >y
    -0.25
     EVENTS
    -0.24
     Events
    -0.24
     events
    -0.24
    éĥ½ä¸įæķ¢
    -0.24
    ensions
    -0.24
    POSITIVE LOGITS
     cut
    0.27
     instantaneous
    0.26
     optimized
    0.25
     perfect
    0.25
     immediate
    0.25
    ä¼ĺåĮĸ
    0.25
     believable
    0.25
    è¿ħéĢŁ
    0.24
     cutoff
    0.24
    optim
    0.24
    Activations Density 13.131%

    No Known Activations