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. 46396
    Prev
    Next
    INDEX
    Explanations

    research/questions

    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
    èĢIJ
    -0.32
    æķĻèĤ²
    -0.27
    ä¸įçα
    -0.27
    ç²Ł
    -0.26
    latex
    -0.25
    ÑģÑĤÑĭ
    -0.25
    èĢĢ
    -0.24
    aes
    -0.24
    橱
    -0.24
    å°Ĭ
    -0.24
    POSITIVE LOGITS
    imin
    0.28
    åŁºç¡Ģä¸Ĭ
    0.26
    ollapsed
    0.26
    ilog
    0.26
    æīĭä¸ĭ
    0.26
    gency
    0.24
    çļĦåŁºç¡Ģä¸Ĭ
    0.24
     fart
    0.24
     rec
    0.24
     vari
    0.24
    Activations Density 0.058%

    No Known Activations