© 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. 54816
    Prev
    Next
    INDEX
    Explanations

    ^

    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
    äºijéĽĨ
    -0.27
     rag
    -0.25
    Propagation
    -0.25
    ersions
    -0.25
    iers
    -0.25
    羡
    -0.25
     weave
    -0.25
     bru
    -0.24
    Santa
    -0.24
    weed
    -0.24
    POSITIVE LOGITS
     Ur
    0.33
    L
    0.29
    -L
    0.27
    对她
    0.27
    /B
    0.27
     Live
    0.27
    她
    0.26
    æķĻèĤ²
    0.26
    Lo
    0.26
     Lo
    0.26
    Activations Density 0.013%

    No Known Activations