© 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. 23574
    Prev
    Next
    INDEX
    Explanations

    Processes, procedures, rules

    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
    aģı
    -0.28
    жд
    -0.28
    ther
    -0.26
    ufen
    -0.25
    é¬ĥ
    -0.25
    驳
    -0.24
    åłĨ积
    -0.24
    åĬ¨æĦŁ
    -0.24
    æł©
    -0.24
    æĮ¨
    -0.23
    POSITIVE LOGITS
     rules
    0.53
    è§Ħç«łåĪ¶åº¦
    0.52
     policies
    0.47
     regulations
    0.47
    è§ĦåĪĻ
    0.45
    rules
    0.45
     laws
    0.44
     Rules
    0.43
     norms
    0.43
    åĪ¶åº¦
    0.43
    Activations Density 0.008%

    No Known Activations