© 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. 12-TRANSCODER-HP
    7. 21977
    Prev
    Next
    INDEX
    Explanations

    Apostrophes and possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æµģåIJij
    -0.27
    稽
    -0.26
    etta
    -0.26
    eware
    -0.26
     baÅŁÄ±na
    -0.25
    å¹´ä¹ĭ
    -0.24
     apprentices
    -0.24
    .sat
    -0.24
    çĻ£
    -0.24
    oded
    -0.24
    POSITIVE LOGITS
    çĸı
    0.30
     replica
    0.28
     replication
    0.27
    åı«
    0.27
    幸
    0.26
    夹
    0.26
     candidate
    0.26
    å¤įåĪ¶
    0.26
     rug
    0.25
    .rep
    0.25
    Activations Density 0.004%

    No Known Activations