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. 24094
    Prev
    Next
    INDEX
    Explanations

    positive outcomes and living well

    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
     Vig
    -0.27
     Omn
    -0.26
    íĥĿ
    -0.26
    æŀ¶
    -0.26
     Skinner
    -0.25
     '{}
    -0.25
    metric
    -0.25
     è¾ĵ
    -0.25
    鸨
    -0.25
    è¾ĵ
    -0.25
    POSITIVE LOGITS
    eland
    0.26
    å°ij
    0.26
     aure
    0.24
    uzu
    0.24
    ipur
    0.23
    usta
    0.23
     Recipes
    0.23
    æ°¸ä¸į
    0.23
    elu
    0.23
     FAQs
    0.23
    Activations Density 0.001%

    No Known Activations