© 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. 31-TRANSCODER-HP
    7. 19658
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ='_
    -0.25
     discretion
    -0.25
    coe
    -0.24
    çIJ²
    -0.24
    rient
    -0.24
    çļĦå°±æĺ¯
    -0.23
    楯
    -0.23
     Bench
    -0.23
    hyth
    -0.22
    åºĹåĨħ
    -0.22
    POSITIVE LOGITS
    å¸®ä½ł
    0.26
    lique
    0.23
    ices
    0.23
    åħ¶ä½Ļ
    0.23
    æł¼æŀĹ
    0.23
    school
    0.22
    ä½łè¦ģ
    0.22
     aval
    0.22
    mites
    0.22
     adolescence
    0.21
    Activations Density 0.103%

    No Known Activations

    This feature has no known activations.