© 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. 27-TRANSCODER-HP
    7. 56487
    Prev
    Next
    INDEX
    Explanations

    peanut butter

    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
    Negative Logits
    姹
    -0.25
    ctors
    -0.24
    enza
    -0.24
    lda
    -0.24
     favourites
    -0.24
    äu
    -0.23
    æŃ»è§Ĵ
    -0.23
    atically
    -0.23
    ãĤ«ãĥ¼
    -0.23
    olean
    -0.23
    POSITIVE LOGITS
    ä¸Ńæ¯Ĵ
    0.32
    åı¬åĶ¤
    0.25
    YTE
    0.24
    æĬ¤çħ§
    0.24
     REPRESENT
    0.24
    èIJ½
    0.24
    å¥Ĺ
    0.23
    ighb
    0.23
    温åĴĮ
    0.23
     protein
    0.23
    Activations Density 0.007%

    No Known Activations