© 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. 58417
    Prev
    Next
    INDEX
    Explanations

    Adverbs of degree/intensity

    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
    æĽ¿
    -0.26
    ategory
    -0.26
    %</
    -0.26
    nis
    -0.25
     </>↵
    -0.25
     SMART
    -0.25
    mont
    -0.24
     varargin
    -0.24
    ---</
    -0.24
    SMART
    -0.23
    POSITIVE LOGITS
    çļĦå½±åĵį
    0.31
     did
    0.30
    å½±åĵį
    0.29
     influence
    0.27
    å½±åĵįåĬĽçļĦ
    0.27
    å½±éŁ¿
    0.26
    çļĦæĶ¯æĮģ
    0.26
    å¤ĩ
    0.26
    å½±åĵįåĬĽ
    0.25
     Infinite
    0.25
    Activations Density 0.004%

    No Known Activations