© 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. 20-TRANSCODER-HP
    7. 140551
    Prev
    Next
    INDEX
    Explanations

    methods, ways, or strategies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     vines
    -0.27
    å½Ŀ
    -0.27
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.26
    ycl
    -0.25
    >Main
    -0.25
     rot
    -0.25
    æ¿®
    -0.25
    æĸĩä¸Ń
    -0.24
    gon
    -0.24
    >d
    -0.24
    POSITIVE LOGITS
    äºĭä¸ļåıijå±ķ
    0.29
    ç½ijæ°ij
    0.27
    lef
    0.26
    esy
    0.26
    lectic
    0.26
    æľŁåĨħ
    0.26
     alone
    0.25
    ivos
    0.25
    _MSK
    0.24
    ucken
    0.24
    Activations Density 15.813%

    No Known Activations