© 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. 31-TRANSCODER-HP
    7. 18437
    Prev
    Next
    INDEX
    Explanations

    Non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dips
    -0.29
    润æ»ijæ²¹
    -0.28
    nees
    -0.27
     numer
    -0.27
    Fixture
    -0.26
    .transitions
    -0.26
    æĦı大
    -0.26
    OLUMNS
    -0.25
    RSS
    -0.24
    reflection
    -0.24
    POSITIVE LOGITS
    obar
    0.33
    idente
    0.29
    缺åı£
    0.24
    梦è§ģ
    0.24
     MICRO
    0.23
    icide
    0.23
    äºŃ
    0.23
    åħ±
    0.23
    åľ¨ç½ij绾
    0.23
    æķĮ
    0.23
    Activations Density 0.150%

    No Known Activations