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. 65946
    Prev
    Next
    INDEX
    Explanations

    ocom

    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
    pressive
    -0.27
    åį³æĹ¶åıijçĶŁ
    -0.26
    until
    -0.26
    象
    -0.25
    xFF
    -0.25
    .yy
    -0.25
    ʰ
    -0.24
     timeval
    -0.23
    å¼
    -0.23
    ulls
    -0.23
    POSITIVE LOGITS
    èħĶ
    0.26
    å®ŀç͍æĢ§
    0.26
    cores
    0.25
     injector
    0.25
     </>↵
    0.25
    ament
    0.25
     cavity
    0.25
    vue
    0.25
     Attention
    0.24
     technical
    0.24
    Activations Density 0.045%

    No Known Activations