© 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. 163282
    Prev
    Next
    INDEX
    Explanations

    Mixed, unstructured data snippets

    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
    åħ¨åĽ½
    -0.41
     national
    -0.41
     nationwide
    -0.41
     Nationwide
    -0.39
    åĽ½æ°ij
    -0.39
    åĽ½æ°ijç»ıæµİ
    -0.37
    åħ¨ç¤¾ä¼ļ
    -0.35
     nacional
    -0.35
    national
    -0.35
    åľ¨åħ¨åĽ½
    -0.34
    POSITIVE LOGITS
    OTO
    0.34
     worlds
    0.31
     Latin
    0.30
     civilizations
    0.28
     latin
    0.27
     captured
    0.27
     Earth
    0.26
    Latin
    0.26
     remote
    0.25
     Ost
    0.25
    Activations Density 0.001%

    No Known Activations