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. 98029
    Prev
    Next
    INDEX
    Explanations

    event

    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
    ä¸ļåĬ¡
    -0.30
    说
    -0.26
    骨头
    -0.26
    åľŁ
    -0.26
    æ¬ł
    -0.25
     apt
    -0.24
    (e
    -0.24
     pivot
    -0.24
    åıĭ
    -0.24
     flush
    -0.23
    POSITIVE LOGITS
    FML
    0.30
    =o
    0.28
    [](
    0.28
    ",__
    0.27
    ä¾ĭå¤ĸ
    0.26
    大çģ«
    0.26
    羣æŃ£åģļåΰ
    0.26
    ä»ĬçĶŁ
    0.26
    羣çα
    0.25
    [].
    0.25
    Activations Density 0.002%

    No Known Activations