© 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. 22-TRANSCODER-HP
    7. 113186
    Prev
    Next
    INDEX
    Explanations

    Relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĸ¹åı¯
    -0.31
    opia
    -0.28
    æīįèĥ½
    -0.26
    allest
    -0.26
    fois
    -0.26
     nevertheless
    -0.25
    rails
    -0.25
     lest
    -0.24
     cadre
    -0.24
    ä¸įè¦ģ
    -0.24
    POSITIVE LOGITS
     intrinsic
    0.27
    åĹľ
    0.27
     sclerosis
    0.25
    cosystem
    0.25
     inherent
    0.25
    æľīä¿¡å¿ĥ
    0.25
    @show
    0.24
     diss
    0.24
    wish
    0.24
    禧
    0.23
    Activations Density 0.008%

    No Known Activations