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. 11-TRANSCODER-HP
    4. 54556
    Prev
    Next
    INDEX
    Explanations

    software licenses and agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aviour
    -0.27
    çijĽ
    -0.26
     character
    -0.26
     Ñĥг
    -0.24
    izational
    -0.24
    EDGE
    -0.23
    åĺ´
    -0.23
    gener
    -0.23
    ril
    -0.23
    sdale
    -0.23
    POSITIVE LOGITS
     saÄŁlam
    0.28
    _tele
    0.26
    次
    0.25
    ä¼łè¨Ģ
    0.24
     bog
    0.24
     pageInfo
    0.24
     propName
    0.23
    Tai
    0.23
    éķ¿çĽ¸
    0.23
    AllowAnonymous
    0.23
    Activations Density 0.912%

    No Known Activations