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. 10228
    Prev
    Next
    INDEX
    Explanations

    wait

    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
    arrison
    -0.26
    èµĦ
    -0.25
    ’a
    -0.25
    PMENT
    -0.25
    ạn
    -0.24
    ç¾ŀ
    -0.24
    âĨĹ
    -0.24
    åŃĺ
    -0.24
     collectively
    -0.23
    aines
    -0.23
    POSITIVE LOGITS
     genie
    0.29
    è°ģçŁ¥
    0.27
    mö
    0.25
    mits
    0.25
    ingle
    0.24
     <%
    0.24
    Conf
    0.24
    medium
    0.23
     aliqu
    0.23
    acre
    0.23
    Activations Density 0.001%

    No Known Activations