© 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. 14-TRANSCODER-HP
    7. 41774
    Prev
    Next
    INDEX
    Explanations

    common grammatical structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    olon
    -0.26
    çľģ份
    -0.26
     FileType
    -0.25
    缺
    -0.25
    ç§įç±»
    -0.24
    loff
    -0.24
    ñas
    -0.24
    ä¸ĭçıŃ
    -0.24
    æ¯Ķäºļ
    -0.24
    ajas
    -0.24
    POSITIVE LOGITS
    arching
    0.27
     tube
    0.27
     cm
    0.25
    nt
    0.25
    amic
    0.25
     fick
    0.25
    enth
    0.24
    OperationException
    0.24
     CM
    0.24
    Ø®ÙĬ
    0.24
    Activations Density 1.673%

    No Known Activations