© 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. 32-TRANSCODER-HP
    7. 44212
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     screws
    -0.27
    dig
    -0.26
     semantics
    -0.26
    HandlerContext
    -0.26
     sem
    -0.26
     semaphore
    -0.25
    .ObjectModel
    -0.25
    licity
    -0.25
    ä¸į妨
    -0.25
     biên
    -0.25
    POSITIVE LOGITS
    åħµ
    0.29
    achs
    0.27
    ึà¸ģ
    0.27
    æĮĤéĴ©
    0.26
    å±ħ室
    0.26
    pur
    0.26
     reminded
    0.25
    apsed
    0.25
     grabbed
    0.25
     prevented
    0.25
    Activations Density 0.001%

    No Known Activations