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. 65940
    Prev
    Next
    INDEX
    Explanations

    g

    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
    istry
    -0.28
    äºĨè§£ä¸Ģä¸ĭ
    -0.28
    credited
    -0.27
    çłĶåζ
    -0.27
    adow
    -0.27
    ooke
    -0.27
    cer
    -0.26
    .jdesktop
    -0.25
    饰
    -0.25
    crement
    -0.25
    POSITIVE LOGITS
     Composition
    0.27
    ialis
    0.26
    wind
    0.26
    ÏĢ
    0.25
    樵
    0.25
    对该
    0.25
    è¶Ĭæĺ¯
    0.25
    esh
    0.25
    )>>
    0.25
    åĬłä»¥
    0.25
    Activations Density 0.004%

    No Known Activations