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. 66062
    Prev
    Next
    INDEX
    Explanations

    Excerpts from varied sources

    np_max-act · gemini-2.0-flash

    descriptions of historical legal trials, especially dated accounts written in a formal, record-like style.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
    ä¸įå¾Ĺ转载
    -0.29
     Ster
    -0.29
    ä¸įåı¯èĥ½
    -0.26
    çľ¼çļ®
    -0.26
    ãģ¯ãģĤãĤĬãģ¾ãģĽãĤĵ
    -0.25
    è¯įæĿ¡
    -0.25
     Top
    -0.25
    turnstile
    -0.25
     condensed
    -0.24
    -Level
    -0.24
    POSITIVE LOGITS
    oha
    0.30
    æ²Ľ
    0.29
    anke
    0.29
    åĴ§
    0.26
     ipc
    0.26
    ãn
    0.25
    RIPT
    0.25
    iant
    0.25
     IPC
    0.24
    rown
    0.24
    Activations Density 0.006%

    No Known Activations