© 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. 56498
    Prev
    Next
    INDEX
    Explanations

    death and sentencing

    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
    åijĬ
    -0.30
    æ°¨éħ¸
    -0.28
    rias
    -0.28
    èģĬ
    -0.26
    交ä¼ļ
    -0.26
    getManager
    -0.25
    åıijå¸ĥä¼ļ
    -0.25
    è°
    -0.25
    rio
    -0.24
    oodle
    -0.24
    POSITIVE LOGITS
    æŃ»åĪij
    0.27
    åĿļå®ļ
    0.26
    oration
    0.26
    ilor
    0.26
    积æŀģæݨåĬ¨
    0.26
    æ¤į
    0.25
     alive
    0.24
    çļĦ羣å®ŀæĢ§
    0.24
    ıģı
    0.24
     dumpster
    0.24
    Activations Density 0.002%

    No Known Activations