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. 24503
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    ấm
    -0.28
     touching
    -0.27
     touches
    -0.27
     giản
    -0.26
    lia
    -0.26
     Giant
    -0.26
    éªĦåĤ²
    -0.25
    æ²»çIJĨ
    -0.25
    ç®Ģä»ĭ
    -0.24
    ç±´
    -0.24
    POSITIVE LOGITS
    åĬ¡
    0.28
    ä¼ļ议精ç¥ŀ
    0.27
    éĢļçŁ¥ä¹¦
    0.26
    erk
    0.25
    åī¯å¸Ĥéķ¿
    0.25
     epub
    0.24
    еÑģÑģ
    0.24
     compuls
    0.24
    lear
    0.24
    pute
    0.24
    Activations Density 0.004%

    No Known Activations