© 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. 12-TRANSCODER-HP
    7. 22891
    Prev
    Next
    INDEX
    Explanations

    Code, company names, nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    margin
    -0.29
    ä¸īçĤ¹
    -0.28
    人æ°ijæ³ķéĻ¢
    -0.26
    ä¸ī家
    -0.26
    é²ľæĺİ
    -0.26
    è¿Ļä¸ī个
    -0.26
    put
    -0.25
     PendingIntent
    -0.24
    åĬ¨çĶŁæĪIJ
    -0.24
    æĹ©é¤IJ
    -0.24
    POSITIVE LOGITS
    æĹı
    0.31
    arth
    0.29
    çĽĬ
    0.29
    .every
    0.28
    oble
    0.27
    opol
    0.26
    cht
    0.26
    ilih
    0.25
    zos
    0.25
     anth
    0.25
    Activations Density 0.002%

    No Known Activations