© 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. 33-TRANSCODER-HP
    7. 52691
    Prev
    Next
    INDEX
    Explanations

    Verify/verification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Block
    -0.32
     block
    -0.31
     Blocks
    -0.30
    block
    -0.29
    Blocks
    -0.28
    åĿĹ
    -0.28
     blocks
    -0.28
    Block
    -0.28
    .getBlock
    -0.27
    blk
    -0.26
    POSITIVE LOGITS
     ver
    0.44
     verify
    0.42
     verifying
    0.40
    éªĮè¯ģ
    0.39
    Verify
    0.38
     Verify
    0.37
    Verifier
    0.37
     verification
    0.36
     Verified
    0.36
     verified
    0.35
    Activations Density 0.035%

    No Known Activations