© 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. 23634
    Prev
    Next
    INDEX
    Explanations

    the

    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
    other
    -0.34
     other
    -0.33
    åħ¶ä»ĸ
    -0.32
    others
    -0.30
    aff
    -0.29
     lain
    -0.28
    ä¸İåħ¶ä»ĸ
    -0.28
    affe
    -0.28
    åħ¶å®ĥ
    -0.28
    Other
    -0.27
    POSITIVE LOGITS
    URN
    0.30
     Universal
    0.28
    Universal
    0.28
    åĪ«è¯´
    0.28
    жд
    0.26
    æĸ¯åŁº
    0.25
    ç´Ļ
    0.24
    mı
    0.24
     Ukrainian
    0.23
    гÑĢамм
    0.23
    Activations Density 0.004%

    No Known Activations