© 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. 163171
    Prev
    Next
    INDEX
    Explanations

    which that

    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
    çļĦæĺ¯
    -0.48
    çļĦå°±æĺ¯
    -0.37
     includes
    -0.37
    å°±åľ¨äºİ
    -0.35
     involves
    -0.34
    åľ¨äºİ
    -0.33
    èĢħãģ¯
    -0.33
    ìŀIJëĬĶ
    -0.32
    ãĤĭãģ®ãģ¯
    -0.32
    ìĹIJëĬĶ
    -0.32
    POSITIVE LOGITS
    æľīä¸įå°ij
    0.29
    ä¸įå°ij人
    0.29
    éĩįçĤ¹åħ³æ³¨
    0.28
     quite
    0.28
    utsche
    0.27
    stery
    0.27
    (stage
    0.26
    lish
    0.25
    VELO
    0.24
    åįģ足
    0.24
    Activations Density 0.004%

    No Known Activations