Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 146308
    Prev
    Next
    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebHost
    -0.28
    ScreenState
    -0.27
    -of
    -0.25
    åįĹè·¯
    -0.25
     waters
    -0.24
    >({
    -0.24
    缣
    -0.24
    ób
    -0.23
    ustralian
    -0.23
    ä¹ĭ乡
    -0.23
    POSITIVE LOGITS
    åģ¶
    0.29
    åĤħ
    0.26
    ables
    0.26
    èµıæŀIJ
    0.25
     Pruitt
    0.25
    fighter
    0.25
    çĭ¬
    0.25
     coherence
    0.24
    iero
    0.24
    ä¾µåįł
    0.24
    Activations Density 0.258%

    No Known Activations