© 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. 23-TRANSCODER-HP
    7. 25382
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĶļèĩ³
    -0.31
    Ñģоб
    -0.28
    éĩį
    -0.28
    åıŁ
    -0.25
    _tC
    -0.25
    æĭĨè¿ģ
    -0.25
    ãng
    -0.25
    uja
    -0.25
    çĶļèĩ³æĺ¯
    -0.25
     Sticky
    -0.25
    POSITIVE LOGITS
    ä¸Ģä½ĵåĮĸ
    0.32
    综åIJĪ
    0.31
    綾åIJĪ
    0.29
     unified
    0.29
     practical
    0.29
    illion
    0.29
    åı°éĺ¶
    0.28
    éĺ¶æ¢¯
    0.28
     professionally
    0.28
     combined
    0.27
    Activations Density 0.016%

    No Known Activations