© 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. 27-TRANSCODER-HP
    7. 58065
    Prev
    Next
    INDEX
    Explanations

    code/system prompts

    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
    subs
    -0.28
    exus
    -0.26
     subsidy
    -0.26
     subsid
    -0.26
    Ě
    -0.25
    ious
    -0.25
    culator
    -0.25
    ãĥĭãĥ¥ãĥ¼ãĤ¹
    -0.25
     gamble
    -0.25
    bsub
    -0.25
    POSITIVE LOGITS
    å¿ĥä¸ŃçļĦ
    0.34
    å¿ĥéĩĮ
    0.34
    å¿ĥä¸Ń
    0.33
     frustrations
    0.31
    åij¼
    0.29
    夺
    0.29
     frustration
    0.29
    临
    0.28
    æĥħ绪
    0.28
    æģ¨
    0.28
    Activations Density 0.002%

    No Known Activations