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. 7-TRANSCODER-HP
    4. 97817
    Prev
    Next
    INDEX
    Explanations

    respiration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bis
    -0.29
     WrocÅĤaw
    -0.24
    çĹĴ
    -0.24
    eyes
    -0.24
     Rit
    -0.23
     Spi
    -0.23
     relative
    -0.23
    .si
    -0.23
    ')."
    -0.23
     zf
    -0.23
    POSITIVE LOGITS
    gil
    0.33
    lobal
    0.30
       
    0.29
    éĨĮ
    0.27
     Guarantee
    0.27
     MEP
    0.26
    寡
    0.26
    éļ§
    0.25
     Associates
    0.25
    æī«ä¸Ģæī«
    0.24
    Activations Density 0.001%

    No Known Activations