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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88725
    Prev
    Next
    INDEX
    Explanations

    Art, history, cultural movements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anto
    -0.32
     Companion
    -0.27
    ä¸įæĸŃå¢ŀ强
    -0.25
    è§ı
    -0.25
    ByExample
    -0.25
    绽
    -0.25
    驹
    -0.25
    ADDRESS
    -0.24
    è¿Ľåľº
    -0.24
    å¤ĩ注
    -0.24
    POSITIVE LOGITS
    å¸Ĥåľºä¸Ĭ
    0.31
    çĽ¸ä¼¼
    0.28
    缸è¿ij
    0.28
    chosen
    0.27
     chosen
    0.26
    æĹ¢çĦ¶
    0.26
    群ä½ĵ
    0.26
    ettes
    0.25
    enses
    0.24
     fourth
    0.24
    Activations Density 10.663%

    No Known Activations