© 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. 88325
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    Negative Logits
    çļĦæĦıè§ģ
    -0.25
     Reason
    -0.25
     AGAIN
    -0.25
    ä¸įèĥ½åĨį
    -0.24
    æł¹
    -0.24
    ä¸Ĭ次
    -0.24
    æĦıè§ģ
    -0.24
    å¦Ħ
    -0.24
     opinion
    -0.23
    lagen
    -0.23
    POSITIVE LOGITS
    é«ĺ强度
    0.29
    unami
    0.27
    é«ĺæ¸ħ
    0.27
    æİĴåºı
    0.26
    è´
    0.26
    _compress
    0.26
    ulary
    0.25
    gettext
    0.25
    ridge
    0.25
    èĨ³
    0.25
    Activations Density 8.106%

    No Known Activations