© 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. 108699
    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
     ourselves
    -0.25
    sel
    -0.25
    ãĥ£
    -0.24
    åij±
    -0.23
    cess
    -0.23
    cales
    -0.23
    quette
    -0.23
     metab
    -0.23
    åIJĦå¼Ĥ
    -0.23
    å¤įå·¥å¤į
    -0.23
    POSITIVE LOGITS
    æ¯Ķ
    0.24
     AFC
    0.24
    onto
    0.24
     monoc
    0.24
    çĻ»
    0.24
    RFC
    0.24
    åī¯
    0.23
    ificant
    0.23
    alloc
    0.23
    dash
    0.23
    Activations Density 17.159%

    No Known Activations