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. 97824
    Prev
    Next
    INDEX
    Explanations

    S

    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
    åѦçĶŁçļĦ
    -0.29
    arat
    -0.26
    æĤ£èĢħçļĦ
    -0.25
    åĪĨè¡Į
    -0.25
    让åѦçĶŁ
    -0.24
    æĶ¯è¡Į
    -0.24
     Patient
    -0.24
     Aff
    -0.24
    Patient
    -0.24
     Alloc
    -0.23
    POSITIVE LOGITS
    éĽĦ
    0.27
    æ¶īåıĬ
    0.24
    æķ¢
    0.24
    ê¸Ģ
    0.24
    ä¾µ
    0.24
    bases
    0.24
     unic
    0.24
    ằm
    0.24
    elsinki
    0.24
     james
    0.24
    Activations Density 0.000%

    No Known Activations