© 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. 24252
    Prev
    Next
    INDEX
    Explanations

    gent

    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
    人群
    -0.30
    ç²ĴåŃIJ
    -0.27
    åĪļ
    -0.25
    ä¹ĹãĤĬ
    -0.25
    å½
    -0.24
    ailer
    -0.24
    ä¸Ĭè°ĥ
    -0.24
    /rest
    -0.24
     finale
    -0.24
    æĭ¨
    -0.24
    POSITIVE LOGITS
    née
    0.34
    zie
    0.26
    nego
    0.25
    注æĺİåĩºå¤Ħ
    0.25
    æİĺ
    0.24
    åĮIJ
    0.24
    né
    0.24
    .getBean
    0.24
    SourceType
    0.24
    abytes
    0.23
    Activations Density 0.001%

    No Known Activations