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. 24115
    Prev
    Next
    INDEX
    Explanations

    craft

    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
    ä¹Łæ²¡
    -0.29
    ä¸į代表
    -0.29
    çon
    -0.27
    _URL
    -0.26
    æīĢæīĢ
    -0.25
    ä¸Ģä½ĵåĮĸ
    -0.25
    ä¹Łæ²¡æľī
    -0.24
     crossAxisAlignment
    -0.24
    setContent
    -0.24
    没æľīä»»ä½ķ
    -0.24
    POSITIVE LOGITS
     guardian
    0.26
    ä¼ł
    0.26
    -fly
    0.26
    _PTR
    0.25
     Hurt
    0.25
    æĸ°æµª
    0.24
    -next
    0.24
    è¿ŀéĶģ
    0.24
    严å¯Ĩ
    0.24
    åīįä¸ĸ
    0.23
    Activations Density 0.002%

    No Known Activations