© 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. 18419
    Prev
    Next
    INDEX
    Explanations

    code questions

    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
    êµIJ
    -0.31
    æķĪæŀľ
    -0.28
    adel
    -0.28
     mask
    -0.27
     Moon
    -0.26
    ä¹Ļ
    -0.26
    åĵ¥ä¼¦æ¯Ķäºļ
    -0.26
    çļĵ
    -0.25
    åıijçĶŁçļĦ
    -0.25
    模æĿ¿
    -0.25
    POSITIVE LOGITS
    éļ°
    0.27
    fuse
    0.27
     Stub
    0.26
    поÑĤен
    0.26
    ForgeryToken
    0.25
    æ½ľèĥ½
    0.24
    诤
    0.24
    Fuse
    0.24
    èĥ½éĩı
    0.24
    人æīį
    0.23
    Activations Density 0.174%

    No Known Activations