© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108304
    Prev
    Next
    INDEX
    Explanations

    emotional situations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    лиÑĤ
    -0.26
    妾
    -0.26
    rames
    -0.25
    vik
    -0.25
    .plist
    -0.24
    æŀŃ
    -0.24
    emia
    -0.24
    çļ±çº¹
    -0.23
     cov
    -0.23
    _ins
    -0.23
    POSITIVE LOGITS
     commute
    0.29
    å·¥ä¸ļ大åѦ
    0.28
    avor
    0.27
    çĶŁæ´»çļĦ
    0.26
    ä¸ĸçķĮçļĦ
    0.25
    à¹Īะ
    0.25
    bens
    0.25
    ä¿ĥè¿Ľ
    0.25
     comm
    0.24
    ä½ıåľ¨
    0.24
    Activations Density 21.247%

    No Known Activations