© 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. 58327
    Prev
    Next
    INDEX
    Explanations

    jail

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¹å¼ıè¿Ľè¡Į
    -0.30
    æ°ijä¼Ĺ
    -0.28
     fences
    -0.27
    aldo
    -0.27
    æ³ķå¾ĭè§Ħå®ļ
    -0.27
    \Schema
    -0.26
    addField
    -0.26
    社ä¼ļåıijå±ķ
    -0.26
     observers
    -0.26
     borders
    -0.26
    POSITIVE LOGITS
    stub
    0.28
    ä¹īåĬ¡
    0.28
    izable
    0.27
    áĥĺ
    0.26
    æ½ľåĬĽ
    0.26
    hub
    0.25
    .Microsoft
    0.25
    gradable
    0.25
     rates
    0.25
    åı¯çĸij
    0.25
    Activations Density 0.004%

    No Known Activations