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. 46405
    Prev
    Next
    INDEX
    Explanations

    exacerb

    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
     bÅĤ
    -0.31
    ä¼ģ
    -0.28
     scaleX
    -0.26
    uct
    -0.26
    è°ĥ
    -0.26
    éĻĪè¿°
    -0.26
     Balance
    -0.25
     colleague
    -0.25
    X
    -0.25
    ä¼łç»ŁçļĦ
    -0.24
    POSITIVE LOGITS
    è¦ģçľĭ
    0.28
    acier
    0.27
    ROME
    0.27
    ç½Ĺæĸ¯
    0.26
    æŃ¤æ¡Ī
    0.26
    对ä»ĸ们
    0.26
    åł¡åŀĴ
    0.25
    èĭĩ
    0.25
     Naomi
    0.25
     sno
    0.25
    Activations Density 0.387%

    No Known Activations