© 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. 22-TRANSCODER-HP
    7. 128981
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -go
    -0.27
    ongs
    -0.27
    ong
    -0.27
    以åıĬ
    -0.26
     flies
    -0.25
    alf
    -0.24
    Hom
    -0.23
    axis
    -0.23
     Hold
    -0.23
    -road
    -0.23
    POSITIVE LOGITS
    è¿ĻçĤ¹
    0.27
    说ä»Ģä¹Ī
    0.27
    adamente
    0.27
    íĮIJ
    0.26
    ument
    0.26
    æī¹åıijå¸Ĥåľº
    0.26
    è¿Ļä¸ĢçĤ¹
    0.25
    åIJĥäºı
    0.24
     category
    0.24
    Category
    0.24
    Activations Density 0.001%

    No Known Activations