© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88416
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obot
    -0.28
    isos
    -0.26
    注æĺİæĿ¥æºIJ
    -0.26
    headed
    -0.25
    ifies
    -0.25
    ioc
    -0.24
    ä¸Ģ缴éĥ½æĺ¯
    -0.23
     Hoffman
    -0.23
    otes
    -0.23
    SJ
    -0.23
    POSITIVE LOGITS
    项
    0.28
    该æĢİä¹ĪåĬŀ
    0.28
     quick
    0.27
     f
    0.26
     incid
    0.26
    ale
    0.26
    trand
    0.26
    íħĢ
    0.25
    åı¹äºĨ
    0.25
     find
    0.25
    Activations Density 6.945%

    No Known Activations