© 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. 12-TRANSCODER-HP
    7. 21951
    Prev
    Next
    INDEX
    Explanations

    Spanish/Portuguese questions

    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
    Negative Logits
    -dot
    -0.28
     supern
    -0.28
    åIJĮå¹´
    -0.27
    dney
    -0.26
    #End
    -0.26
    olog
    -0.26
    æķ²
    -0.25
    bió
    -0.25
    nesty
    -0.24
     Richt
    -0.24
    POSITIVE LOGITS
    etable
    0.28
    å°ıä¼ĻåŃIJ
    0.26
    FFE
    0.26
    ãĥ¬ãĥĵãĥ¥ãĥ¼
    0.26
    UNITY
    0.25
    æ³»
    0.25
     athe
    0.25
    æľĢç¾İçļĦ
    0.25
    .loop
    0.25
    .less
    0.25
    Activations Density 0.002%

    No Known Activations