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. 98037
    Prev
    Next
    INDEX
    Explanations

    Diverse text snippets

    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
    covers
    -0.27
    éĺ´å½±
    -0.25
    suppress
    -0.25
    .sheet
    -0.25
    å°ģ
    -0.24
    nos
    -0.24
    就好
    -0.24
     seal
    -0.24
    NV
    -0.24
     ref
    -0.24
    POSITIVE LOGITS
    åħ¥å¸Ĥ
    0.29
    丰å¯Į
    0.27
    atel
    0.27
    INDER
    0.26
    ä¸Ĭ线
    0.25
    panion
    0.24
    æIJĶ
    0.24
    OTE
    0.24
     assignments
    0.24
    aments
    0.24
    Activations Density 0.001%

    No Known Activations