© 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. 58629
    Prev
    Next
    INDEX
    Explanations

    Spanish place names

    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
     worth
    -0.69
    åĢ¼å¾Ĺ
    -0.62
    éľĢè¦ģ
    -0.57
     important
    -0.56
     Worth
    -0.53
    éĩįè¦ģ
    -0.49
     need
    -0.47
    åĢ¼å¾Ĺä¸Ģ
    -0.45
     Need
    -0.45
    éľĢè¦ģ注æĦı
    -0.44
    POSITIVE LOGITS
    ä¸ĭéĿ¢æĺ¯å°ı
    0.28
    çļĦçĶŁåij½
    0.26
    ä¸įè¿ľå¤Ħ
    0.26
    compressed
    0.25
    çĶŁåij½
    0.25
    åį´è¢«
    0.25
    Ĥ¬
    0.24
    ricular
    0.24
    aryl
    0.24
    .mit
    0.24
    Activations Density 0.004%

    No Known Activations