© 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. 30-TRANSCODER-HP
    7. 94916
    Prev
    Next
    INDEX
    Explanations

    Greek letters, programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æī©æķ£
    -0.30
    clave
    -0.29
     diffusion
    -0.29
     diffuse
    -0.28
     Mad
    -0.27
    plane
    -0.26
     plane
    -0.26
    å¼Ģè¾Ł
    -0.26
    é¦Ī
    -0.26
    ideos
    -0.26
    POSITIVE LOGITS
    lambda
    0.30
    OLE
    0.29
    èį·
    0.28
     lambda
    0.27
     λ
    0.27
     Ko
    0.25
    è¹Ħ
    0.25
     syn
    0.25
    =lambda
    0.25
     senses
    0.25
    Activations Density 0.101%

    No Known Activations