© 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. 27-TRANSCODER-HP
    7. 9653
    Prev
    Next
    INDEX
    Explanations

    Licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Protection
    -0.32
     privacy
    -0.32
    éļIJç§ģ
    -0.30
    ä¿ĿæĬ¤
    -0.30
     protection
    -0.30
    Protection
    -0.30
    privacy
    -0.29
    æ³Į
    -0.27
     protect
    -0.27
    ä¿ĿèŃ·
    -0.27
    POSITIVE LOGITS
    atu
    0.27
    rick
    0.26
     leth
    0.26
    è¯Ń
    0.25
    compet
    0.24
    orth
    0.24
    å·®åĪ«
    0.24
    å¼¹æĢ§
    0.24
    asket
    0.24
    reat
    0.23
    Activations Density 0.021%

    No Known Activations