© 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. 17762
    Prev
    Next
    INDEX
    Explanations

    random information

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    bü
    -0.37
    ä¸ĭæ»ij
    -0.28
    SCO
    -0.27
     din
    -0.26
    æłĩåĩĨ
    -0.25
    å¹ķ
    -0.25
    éĢIJ
    -0.25
     mantle
    -0.25
    vara
    -0.25
    çī½
    -0.25
    POSITIVE LOGITS
    NEL
    0.26
    YLON
    0.25
     CONTRIBUT
    0.24
    è¿ŀ线
    0.24
     virt
    0.23
     ApplicationController
    0.23
     mast
    0.23
     TestUtils
    0.23
    STRUCTIONS
    0.23
    cff
    0.23
    Activations Density 0.608%

    No Known Activations