© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162682
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory issues

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fart
    -0.31
     KH
    -0.29
    æĬ½
    -0.26
    笺
    -0.26
    elic
    -0.26
    iali
    -0.25
    altar
    -0.24
     Weekend
    -0.24
    KH
    -0.24
     garn
    -0.23
    POSITIVE LOGITS
     regulated
    0.40
     historically
    0.33
    regulated
    0.33
     regulation
    0.31
    çĽij管
    0.31
     Regulation
    0.30
     regulating
    0.30
     regulatory
    0.29
     historic
    0.29
     regulations
    0.28
    Activations Density 0.001%

    No Known Activations