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. 93124
    Prev
    Next
    INDEX
    Explanations

    forum posts/code

    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
    atori
    -0.28
    éĢĤ度
    -0.26
    ä¿ĿèŃī
    -0.25
    atto
    -0.24
    though
    -0.24
    ä¿Ŀè¯ģ
    -0.24
    strom
    -0.24
     tor
    -0.23
    unsch
    -0.23
    fur
    -0.23
    POSITIVE LOGITS
     ifs
    0.28
     vin
    0.26
    mts
    0.26
    æĮĩåIJij
    0.25
    Vin
    0.25
    å¹¶äºİ
    0.24
     Johns
    0.24
    vfs
    0.24
    çļĦçłĶåıij
    0.24
    ñe
    0.24
    Activations Density 0.003%

    No Known Activations