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. 98101
    Prev
    Next
    INDEX
    Explanations

    through

    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
    è¶£
    -0.28
     abroad
    -0.27
    èįīèİĵ
    -0.26
    媳å¦ĩ
    -0.26
    èĭŀ
    -0.25
    erer
    -0.25
    ney
    -0.25
    wick
    -0.25
    æĩĤå¾Ĺ
    -0.24
    omon
    -0.24
    POSITIVE LOGITS
     Mae
    0.25
    ãİĿ
    0.25
     \/
    0.24
    âĻĤ
    0.24
    fighter
    0.23
    uala
    0.23
     fou
    0.23
    знак
    0.23
    olumn
    0.23
     geral
    0.23
    Activations Density 0.002%

    No Known Activations